Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1168 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5957. Min Act: -0.1700
Data Index: 5195537 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.5019. Min Act: -0.1700
Data Index: 6740714 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4082. Min Act: -0.1700
Data Index: 3909500 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.3769. Min Act: -0.1700
Data Index: 5290481 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4082. Min Act: -0.1700
Data Index: 6715460 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4394. Min Act: -0.1700
Data Index: 5132062 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.4394. Min Act: -0.1700
Data Index: 4163397 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.3769. Min Act: -0.1700
Data Index: 1889683 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.3769. Min Act: -0.1700
Data Index: 2138377 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.3457. Min Act: -0.1700
Data Index: 2826026 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.3144. Min Act: -0.1700
Data Index: 7960136 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.3144. Min Act: -0.1700
Data Index: 898516 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.3144. Min Act: -0.1700
Data Index: 4314995 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.3144. Min Act: -0.1700
Data Index: 2445058 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.2832. Min Act: -0.1700
Data Index: 5093076 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.3144. Min Act: -0.1700
Data Index: 8716261 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.3144. Min Act: -0.1700
Data Index: 6226929 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.3144. Min Act: -0.1700
Data Index: 6555344 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.3144. Min Act: -0.1700
Data Index: 1116759 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5957. Min Range: -4.5957
Max Act: 4.3144. Min Act: -0.1700
Data Index: 4286670 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19