Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2935 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9447. Min Range: -8.9447
Max Act: 8.9447. Min Act: -0.1700
Data Index: 6468693 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9447. Min Range: -8.9447
Max Act: 8.7572. Min Act: -0.1700
Data Index: 6336037 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9447. Min Range: -8.9447
Max Act: 8.5697. Min Act: -0.1700
Data Index: 4009813 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9447. Min Range: -8.9447
Max Act: 8.5697. Min Act: -0.1700
Data Index: 4305912 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9447. Min Range: -8.9447
Max Act: 8.5072. Min Act: -0.1700
Data Index: 8824816 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9447. Min Range: -8.9447
Max Act: 8.4447. Min Act: -0.1700
Data Index: 3354765 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9447. Min Range: -8.9447
Max Act: 8.4447. Min Act: -0.1700
Data Index: 1957011 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9447. Min Range: -8.9447
Max Act: 8.3822. Min Act: -0.1700
Data Index: 1001563 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9447. Min Range: -8.9447
Max Act: 8.3822. Min Act: -0.1700
Data Index: 5683907 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9447. Min Range: -8.9447
Max Act: 8.3822. Min Act: -0.1700
Data Index: 5478740 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9447. Min Range: -8.9447
Max Act: 8.3197. Min Act: -0.1700
Data Index: 6331503 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9447. Min Range: -8.9447
Max Act: 8.3197. Min Act: -0.1700
Data Index: 7570060 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9447. Min Range: -8.9447
Max Act: 8.3197. Min Act: -0.1700
Data Index: 40257 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9447. Min Range: -8.9447
Max Act: 8.2572. Min Act: -0.1700
Data Index: 7127150 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9447. Min Range: -8.9447
Max Act: 8.2572. Min Act: -0.1700
Data Index: 3135948 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9447. Min Range: -8.9447
Max Act: 8.2572. Min Act: -0.1700
Data Index: 8057200 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9447. Min Range: -8.9447
Max Act: 8.3197. Min Act: -0.1700
Data Index: 7755402 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9447. Min Range: -8.9447
Max Act: 8.2572. Min Act: -0.1700
Data Index: 3922213 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9447. Min Range: -8.9447
Max Act: 8.2572. Min Act: -0.1700
Data Index: 2546073 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9447. Min Range: -8.9447
Max Act: 8.1947. Min Act: -0.1700
Data Index: 6471001 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19