Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4462 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3064. Min Range: -6.3064
Max Act: 6.3064. Min Act: -0.1700
Data Index: 5608917 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3064. Min Range: -6.3064
Max Act: 6.2752. Min Act: -0.1700
Data Index: 515794 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3064. Min Range: -6.3064
Max Act: 6.2752. Min Act: -0.1700
Data Index: 4164851 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3064. Min Range: -6.3064
Max Act: 6.0564. Min Act: -0.1700
Data Index: 6108667 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3064. Min Range: -6.3064
Max Act: 6.0564. Min Act: -0.1700
Data Index: 1377028 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3064. Min Range: -6.3064
Max Act: 6.0252. Min Act: -0.1700
Data Index: 1090642 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3064. Min Range: -6.3064
Max Act: 6.0252. Min Act: -0.1700
Data Index: 4535561 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3064. Min Range: -6.3064
Max Act: 6.0252. Min Act: -0.1700
Data Index: 5990315 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3064. Min Range: -6.3064
Max Act: 5.9314. Min Act: -0.1700
Data Index: 7955318 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3064. Min Range: -6.3064
Max Act: 5.9314. Min Act: -0.1700
Data Index: 8241855 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3064. Min Range: -6.3064
Max Act: 5.9314. Min Act: -0.1700
Data Index: 4026067 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3064. Min Range: -6.3064
Max Act: 5.9002. Min Act: -0.1700
Data Index: 5275446 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3064. Min Range: -6.3064
Max Act: 5.9002. Min Act: -0.1700
Data Index: 3799893 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3064. Min Range: -6.3064
Max Act: 5.9002. Min Act: -0.1700
Data Index: 5361300 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3064. Min Range: -6.3064
Max Act: 5.9002. Min Act: -0.1700
Data Index: 2760382 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3064. Min Range: -6.3064
Max Act: 5.8689. Min Act: -0.1700
Data Index: 7529576 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3064. Min Range: -6.3064
Max Act: 5.8689. Min Act: -0.1700
Data Index: 2855664 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3064. Min Range: -6.3064
Max Act: 5.9002. Min Act: -0.1700
Data Index: 5432670 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3064. Min Range: -6.3064
Max Act: 5.8377. Min Act: -0.1700
Data Index: 4650463 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3064. Min Range: -6.3064
Max Act: 5.8377. Min Act: -0.1700
Data Index: 3707733 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19