Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2416 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1930. Min Range: -5.1930
Max Act: 5.1930. Min Act: -0.1700
Data Index: 4605021 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1930. Min Range: -5.1930
Max Act: 5.0992. Min Act: -0.1700
Data Index: 6490157 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1930. Min Range: -5.1930
Max Act: 5.0055. Min Act: -0.1700
Data Index: 4870333 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1930. Min Range: -5.1930
Max Act: 4.9117. Min Act: -0.1700
Data Index: 5608778 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1930. Min Range: -5.1930
Max Act: 4.8180. Min Act: -0.1700
Data Index: 7032887 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1930. Min Range: -5.1930
Max Act: 4.7555. Min Act: -0.1700
Data Index: 3585199 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1930. Min Range: -5.1930
Max Act: 4.7242. Min Act: -0.1700
Data Index: 8073725 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1930. Min Range: -5.1930
Max Act: 4.7242. Min Act: -0.1700
Data Index: 2038209 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1930. Min Range: -5.1930
Max Act: 4.7242. Min Act: -0.1700
Data Index: 5611600 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1930. Min Range: -5.1930
Max Act: 4.6617. Min Act: -0.1700
Data Index: 1276860 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1930. Min Range: -5.1930
Max Act: 4.6930. Min Act: -0.1700
Data Index: 6863246 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1930. Min Range: -5.1930
Max Act: 4.6617. Min Act: -0.1700
Data Index: 7462493 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1930. Min Range: -5.1930
Max Act: 4.6617. Min Act: -0.1700
Data Index: 1840495 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1930. Min Range: -5.1930
Max Act: 4.6617. Min Act: -0.1700
Data Index: 2052028 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1930. Min Range: -5.1930
Max Act: 4.6305. Min Act: -0.1700
Data Index: 6922784 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1930. Min Range: -5.1930
Max Act: 4.5992. Min Act: -0.1700
Data Index: 2543134 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1930. Min Range: -5.1930
Max Act: 4.6305. Min Act: -0.1700
Data Index: 8631422 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1930. Min Range: -5.1930
Max Act: 4.5992. Min Act: -0.1700
Data Index: 6849367 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1930. Min Range: -5.1930
Max Act: 4.6305. Min Act: -0.1700
Data Index: 2659868 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1930. Min Range: -5.1930
Max Act: 4.5992. Min Act: -0.1700
Data Index: 2054592 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19