Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4368 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9834. Min Range: -3.9834
Max Act: 3.9834. Min Act: -0.1700
Data Index: 5938832 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9834. Min Range: -3.9834
Max Act: 3.9834. Min Act: -0.1700
Data Index: 1613495 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9834. Min Range: -3.9834
Max Act: 3.9834. Min Act: -0.1700
Data Index: 6889216 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9834. Min Range: -3.9834
Max Act: 3.8270. Min Act: -0.1700
Data Index: 8704944 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9834. Min Range: -3.9834
Max Act: 3.7958. Min Act: -0.1700
Data Index: 3434250 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9834. Min Range: -3.9834
Max Act: 3.7958. Min Act: -0.1700
Data Index: 1294853 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9834. Min Range: -3.9834
Max Act: 3.7958. Min Act: -0.1700
Data Index: 267174 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9834. Min Range: -3.9834
Max Act: 3.7958. Min Act: -0.1700
Data Index: 568469 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9834. Min Range: -3.9834
Max Act: 3.7645. Min Act: -0.1700
Data Index: 890416 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9834. Min Range: -3.9834
Max Act: 3.7645. Min Act: -0.1700
Data Index: 4275468 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9834. Min Range: -3.9834
Max Act: 3.7645. Min Act: -0.1700
Data Index: 4089786 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9834. Min Range: -3.9834
Max Act: 3.7958. Min Act: -0.1700
Data Index: 7484802 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9834. Min Range: -3.9834
Max Act: 3.7332. Min Act: -0.1700
Data Index: 4248899 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9834. Min Range: -3.9834
Max Act: 3.7332. Min Act: -0.1700
Data Index: 4210446 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9834. Min Range: -3.9834
Max Act: 3.7019. Min Act: -0.1700
Data Index: 7818496 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9834. Min Range: -3.9834
Max Act: 3.7019. Min Act: -0.1700
Data Index: 3885996 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9834. Min Range: -3.9834
Max Act: 3.7332. Min Act: -0.1700
Data Index: 8133549 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9834. Min Range: -3.9834
Max Act: 3.7019. Min Act: -0.1700
Data Index: 600531 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9834. Min Range: -3.9834
Max Act: 3.7019. Min Act: -0.1700
Data Index: 5839938 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9834. Min Range: -3.9834
Max Act: 3.7019. Min Act: -0.1700
Data Index: 3367220 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19