Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2058 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.3071. Min Range: -9.3071
Max Act: 9.3071. Min Act: -0.1700
Data Index: 6706020 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3071. Min Range: -9.3071
Max Act: 9.3071. Min Act: -0.1700
Data Index: 4791529 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3071. Min Range: -9.3071
Max Act: 9.3071. Min Act: -0.1700
Data Index: 7781605 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3071. Min Range: -9.3071
Max Act: 9.1821. Min Act: -0.1700
Data Index: 6596126 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3071. Min Range: -9.3071
Max Act: 9.1821. Min Act: -0.1700
Data Index: 2951507 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3071. Min Range: -9.3071
Max Act: 9.1821. Min Act: -0.1700
Data Index: 3324444 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3071. Min Range: -9.3071
Max Act: 9.1821. Min Act: -0.1700
Data Index: 2462283 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3071. Min Range: -9.3071
Max Act: 9.0571. Min Act: -0.1700
Data Index: 4281060 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3071. Min Range: -9.3071
Max Act: 9.1196. Min Act: -0.1700
Data Index: 4386016 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3071. Min Range: -9.3071
Max Act: 8.9946. Min Act: -0.1700
Data Index: 1945641 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3071. Min Range: -9.3071
Max Act: 8.9946. Min Act: -0.1700
Data Index: 4960006 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3071. Min Range: -9.3071
Max Act: 8.9946. Min Act: -0.1700
Data Index: 5594996 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3071. Min Range: -9.3071
Max Act: 8.9321. Min Act: -0.1700
Data Index: 3386964 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3071. Min Range: -9.3071
Max Act: 8.9321. Min Act: -0.1700
Data Index: 3391248 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3071. Min Range: -9.3071
Max Act: 8.9321. Min Act: -0.1700
Data Index: 4335016 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3071. Min Range: -9.3071
Max Act: 8.9321. Min Act: -0.1700
Data Index: 4848147 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3071. Min Range: -9.3071
Max Act: 8.8696. Min Act: -0.1700
Data Index: 2055843 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3071. Min Range: -9.3071
Max Act: 8.8696. Min Act: -0.1700
Data Index: 2536658 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3071. Min Range: -9.3071
Max Act: 8.8696. Min Act: -0.1700
Data Index: 4048734 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3071. Min Range: -9.3071
Max Act: 8.8696. Min Act: -0.1700
Data Index: 7179913 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19