Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4866 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7755. Min Range: -5.7755
Max Act: 5.7755. Min Act: -0.1700
Data Index: 8725448 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7755. Min Range: -5.7755
Max Act: 5.7130. Min Act: -0.1700
Data Index: 1581666 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7755. Min Range: -5.7755
Max Act: 5.6505. Min Act: -0.1700
Data Index: 6513785 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7755. Min Range: -5.7755
Max Act: 5.6505. Min Act: -0.1700
Data Index: 681275 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7755. Min Range: -5.7755
Max Act: 5.6192. Min Act: -0.1700
Data Index: 4690562 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7755. Min Range: -5.7755
Max Act: 5.6192. Min Act: -0.1700
Data Index: 2061331 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7755. Min Range: -5.7755
Max Act: 5.5880. Min Act: -0.1700
Data Index: 2501812 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7755. Min Range: -5.7755
Max Act: 5.5880. Min Act: -0.1700
Data Index: 6545780 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7755. Min Range: -5.7755
Max Act: 5.5880. Min Act: -0.1700
Data Index: 3200986 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7755. Min Range: -5.7755
Max Act: 5.5880. Min Act: -0.1700
Data Index: 5466079 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7755. Min Range: -5.7755
Max Act: 5.5880. Min Act: -0.1700
Data Index: 2894097 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7755. Min Range: -5.7755
Max Act: 5.5567. Min Act: -0.1700
Data Index: 8128711 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7755. Min Range: -5.7755
Max Act: 5.5255. Min Act: -0.1700
Data Index: 666703 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7755. Min Range: -5.7755
Max Act: 5.5567. Min Act: -0.1700
Data Index: 1793125 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7755. Min Range: -5.7755
Max Act: 5.5567. Min Act: -0.1700
Data Index: 8407621 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7755. Min Range: -5.7755
Max Act: 5.5567. Min Act: -0.1700
Data Index: 5826897 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7755. Min Range: -5.7755
Max Act: 5.5567. Min Act: -0.1700
Data Index: 5388008 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7755. Min Range: -5.7755
Max Act: 5.5567. Min Act: -0.1700
Data Index: 6607999 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7755. Min Range: -5.7755
Max Act: 5.5255. Min Act: -0.1700
Data Index: 3446165 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7755. Min Range: -5.7755
Max Act: 5.5255. Min Act: -0.1700
Data Index: 3039947 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19