Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 398 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9025. Min Range: -7.9025
Max Act: 7.9025. Min Act: -0.1700
Data Index: 7781249 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9025. Min Range: -7.9025
Max Act: 7.8712. Min Act: -0.1700
Data Index: 1122145 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9025. Min Range: -7.9025
Max Act: 7.8712. Min Act: -0.1700
Data Index: 4962532 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9025. Min Range: -7.9025
Max Act: 7.8712. Min Act: -0.1700
Data Index: 8175939 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9025. Min Range: -7.9025
Max Act: 7.7775. Min Act: -0.1700
Data Index: 7035436 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9025. Min Range: -7.9025
Max Act: 7.7775. Min Act: -0.1700
Data Index: 4379734 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9025. Min Range: -7.9025
Max Act: 7.7150. Min Act: -0.1700
Data Index: 6610597 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9025. Min Range: -7.9025
Max Act: 7.7462. Min Act: -0.1700
Data Index: 565388 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9025. Min Range: -7.9025
Max Act: 7.6212. Min Act: -0.1700
Data Index: 8763975 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9025. Min Range: -7.9025
Max Act: 7.6212. Min Act: -0.1700
Data Index: 7878009 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9025. Min Range: -7.9025
Max Act: 7.6212. Min Act: -0.1700
Data Index: 4193085 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9025. Min Range: -7.9025
Max Act: 7.5587. Min Act: -0.1700
Data Index: 8351739 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9025. Min Range: -7.9025
Max Act: 7.5275. Min Act: -0.1700
Data Index: 4105826 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9025. Min Range: -7.9025
Max Act: 7.5587. Min Act: -0.1700
Data Index: 4689893 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9025. Min Range: -7.9025
Max Act: 7.5275. Min Act: -0.1700
Data Index: 5691036 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9025. Min Range: -7.9025
Max Act: 7.4962. Min Act: -0.1700
Data Index: 5100639 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9025. Min Range: -7.9025
Max Act: 7.4962. Min Act: -0.1700
Data Index: 6961575 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9025. Min Range: -7.9025
Max Act: 7.4962. Min Act: -0.1700
Data Index: 223095 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9025. Min Range: -7.9025
Max Act: 7.4650. Min Act: -0.1700
Data Index: 5238938 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9025. Min Range: -7.9025
Max Act: 7.4650. Min Act: -0.1700
Data Index: 5238939 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19