Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4254 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6671. Min Range: -4.6671
Max Act: 4.6671. Min Act: -0.1700
Data Index: 6230873 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6671. Min Range: -4.6671
Max Act: 4.6358. Min Act: -0.1700
Data Index: 2663933 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6671. Min Range: -4.6671
Max Act: 4.5421. Min Act: -0.1700
Data Index: 3228281 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6671. Min Range: -4.6671
Max Act: 4.5421. Min Act: -0.1700
Data Index: 8181662 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6671. Min Range: -4.6671
Max Act: 4.5108. Min Act: -0.1700
Data Index: 3027815 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6671. Min Range: -4.6671
Max Act: 4.4796. Min Act: -0.1700
Data Index: 4654116 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6671. Min Range: -4.6671
Max Act: 4.4483. Min Act: -0.1700
Data Index: 5315077 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6671. Min Range: -4.6671
Max Act: 4.4483. Min Act: -0.1700
Data Index: 7783915 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6671. Min Range: -4.6671
Max Act: 4.4796. Min Act: -0.1700
Data Index: 7783914 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6671. Min Range: -4.6671
Max Act: 4.4171. Min Act: -0.1700
Data Index: 7530842 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6671. Min Range: -4.6671
Max Act: 4.3858. Min Act: -0.1700
Data Index: 8181661 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6671. Min Range: -4.6671
Max Act: 4.3858. Min Act: -0.1700
Data Index: 3228280 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6671. Min Range: -4.6671
Max Act: 4.3858. Min Act: -0.1700
Data Index: 7783916 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6671. Min Range: -4.6671
Max Act: 4.3858. Min Act: -0.1700
Data Index: 5576664 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6671. Min Range: -4.6671
Max Act: 4.3858. Min Act: -0.1700
Data Index: 7061864 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6671. Min Range: -4.6671
Max Act: 4.3546. Min Act: -0.1700
Data Index: 5845448 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6671. Min Range: -4.6671
Max Act: 4.3546. Min Act: -0.1700
Data Index: 3035240 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6671. Min Range: -4.6671
Max Act: 4.3546. Min Act: -0.1700
Data Index: 3510467 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6671. Min Range: -4.6671
Max Act: 4.3546. Min Act: -0.1700
Data Index: 4317061 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6671. Min Range: -4.6671
Max Act: 4.3233. Min Act: -0.1700
Data Index: 654664 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19