Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2228 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 16.4929. Min Range: -16.4929
Max Act: 16.2429. Min Act: -0.1700
Data Index: 8292030 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.4929. Min Range: -16.4929
Max Act: 16.3679. Min Act: -0.1700
Data Index: 4296930 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.4929. Min Range: -16.4929
Max Act: 16.4929. Min Act: -0.1700
Data Index: 2426861 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.4929. Min Range: -16.4929
Max Act: 14.5554. Min Act: -0.1700
Data Index: 7112149 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.4929. Min Range: -16.4929
Max Act: 14.1179. Min Act: -0.1700
Data Index: 4160604 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.4929. Min Range: -16.4929
Max Act: 15.7429. Min Act: -0.1700
Data Index: 7550708 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.4929. Min Range: -16.4929
Max Act: 15.6179. Min Act: -0.1700
Data Index: 8476553 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.4929. Min Range: -16.4929
Max Act: 16.1179. Min Act: -0.1700
Data Index: 8511769 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.4929. Min Range: -16.4929
Max Act: 14.9304. Min Act: -0.1700
Data Index: 7078474 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.4929. Min Range: -16.4929
Max Act: 15.9304. Min Act: -0.1700
Data Index: 411104 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.4929. Min Range: -16.4929
Max Act: 14.4929. Min Act: -0.1700
Data Index: 7112151 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.4929. Min Range: -16.4929
Max Act: 15.6179. Min Act: -0.1700
Data Index: 1526049 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.4929. Min Range: -16.4929
Max Act: 15.6804. Min Act: -0.1700
Data Index: 2792191 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.4929. Min Range: -16.4929
Max Act: 15.3054. Min Act: -0.1700
Data Index: 2669370 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.4929. Min Range: -16.4929
Max Act: 13.6179. Min Act: -0.1700
Data Index: 5692433 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.4929. Min Range: -16.4929
Max Act: 15.3679. Min Act: -0.1700
Data Index: 7371655 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.4929. Min Range: -16.4929
Max Act: 15.4929. Min Act: -0.1700
Data Index: 1301235 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.4929. Min Range: -16.4929
Max Act: 14.9304. Min Act: -0.1700
Data Index: 955098 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.4929. Min Range: -16.4929
Max Act: 15.3679. Min Act: -0.1700
Data Index: 7075359 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.4929. Min Range: -16.4929
Max Act: 15.3679. Min Act: -0.1700
Data Index: 6571060 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19