Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1636 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4674. Min Range: -5.4674
Max Act: 5.4674. Min Act: -0.1700
Data Index: 3802217 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4674. Min Range: -5.4674
Max Act: 5.4049. Min Act: -0.1700
Data Index: 2467774 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4674. Min Range: -5.4674
Max Act: 5.3111. Min Act: -0.1700
Data Index: 977546 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4674. Min Range: -5.4674
Max Act: 5.2174. Min Act: -0.1700
Data Index: 2098777 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4674. Min Range: -5.4674
Max Act: 5.1861. Min Act: -0.1700
Data Index: 209890 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4674. Min Range: -5.4674
Max Act: 5.1236. Min Act: -0.1700
Data Index: 2346218 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4674. Min Range: -5.4674
Max Act: 5.1549. Min Act: -0.1700
Data Index: 4681323 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4674. Min Range: -5.4674
Max Act: 5.1549. Min Act: -0.1700
Data Index: 4802121 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4674. Min Range: -5.4674
Max Act: 5.1549. Min Act: -0.1700
Data Index: 309346 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4674. Min Range: -5.4674
Max Act: 5.1549. Min Act: -0.1700
Data Index: 2073222 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4674. Min Range: -5.4674
Max Act: 5.0924. Min Act: -0.1700
Data Index: 2214674 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4674. Min Range: -5.4674
Max Act: 5.0924. Min Act: -0.1700
Data Index: 7057276 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4674. Min Range: -5.4674
Max Act: 5.0611. Min Act: -0.1700
Data Index: 5560556 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4674. Min Range: -5.4674
Max Act: 5.0299. Min Act: -0.1700
Data Index: 6991537 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4674. Min Range: -5.4674
Max Act: 5.0299. Min Act: -0.1700
Data Index: 3617771 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4674. Min Range: -5.4674
Max Act: 4.9986. Min Act: -0.1700
Data Index: 4355838 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4674. Min Range: -5.4674
Max Act: 4.9674. Min Act: -0.1700
Data Index: 2458383 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4674. Min Range: -5.4674
Max Act: 4.9674. Min Act: -0.1700
Data Index: 8429944 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4674. Min Range: -5.4674
Max Act: 4.9674. Min Act: -0.1700
Data Index: 667984 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4674. Min Range: -5.4674
Max Act: 4.9361. Min Act: -0.1700
Data Index: 907637 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19