Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 58 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9535. Min Range: -4.9535
Max Act: 4.9535. Min Act: -0.1700
Data Index: 6212027 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9535. Min Range: -4.9535
Max Act: 4.9222. Min Act: -0.1700
Data Index: 5225911 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9535. Min Range: -4.9535
Max Act: 4.8910. Min Act: -0.1700
Data Index: 4399542 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9535. Min Range: -4.9535
Max Act: 4.8597. Min Act: -0.1700
Data Index: 7761133 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9535. Min Range: -4.9535
Max Act: 4.8597. Min Act: -0.1700
Data Index: 2005974 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9535. Min Range: -4.9535
Max Act: 4.8597. Min Act: -0.1700
Data Index: 8107274 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9535. Min Range: -4.9535
Max Act: 4.8285. Min Act: -0.1700
Data Index: 1839230 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9535. Min Range: -4.9535
Max Act: 4.8597. Min Act: -0.1700
Data Index: 3380405 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9535. Min Range: -4.9535
Max Act: 4.8597. Min Act: -0.1700
Data Index: 3953490 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9535. Min Range: -4.9535
Max Act: 4.7972. Min Act: -0.1700
Data Index: 2742135 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9535. Min Range: -4.9535
Max Act: 4.7972. Min Act: -0.1700
Data Index: 5089676 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9535. Min Range: -4.9535
Max Act: 4.7660. Min Act: -0.1700
Data Index: 7682907 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9535. Min Range: -4.9535
Max Act: 4.7972. Min Act: -0.1700
Data Index: 1817137 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9535. Min Range: -4.9535
Max Act: 4.7347. Min Act: -0.1700
Data Index: 6918911 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9535. Min Range: -4.9535
Max Act: 4.7347. Min Act: -0.1700
Data Index: 5222436 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9535. Min Range: -4.9535
Max Act: 4.7660. Min Act: -0.1700
Data Index: 7860360 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9535. Min Range: -4.9535
Max Act: 4.7347. Min Act: -0.1700
Data Index: 8224465 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9535. Min Range: -4.9535
Max Act: 4.7347. Min Act: -0.1700
Data Index: 1927186 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9535. Min Range: -4.9535
Max Act: 4.6722. Min Act: -0.1700
Data Index: 2653697 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9535. Min Range: -4.9535
Max Act: 4.7035. Min Act: -0.1700
Data Index: 2251048 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19