Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4365 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.9036. Min Act: -0.1700
Data Index: 3001039 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.5911. Min Act: -0.1700
Data Index: 6249727 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.5911. Min Act: -0.1700
Data Index: 1728208 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.5911. Min Act: -0.1700
Data Index: 2227996 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.5598. Min Act: -0.1700
Data Index: 401621 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.5598. Min Act: -0.1700
Data Index: 2889520 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.4973. Min Act: -0.1700
Data Index: 4754663 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.4973. Min Act: -0.1700
Data Index: 1040644 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.4661. Min Act: -0.1700
Data Index: 4577209 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.4661. Min Act: -0.1700
Data Index: 3762019 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.4348. Min Act: -0.1700
Data Index: 1790964 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.4036. Min Act: -0.1700
Data Index: 2723086 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.4036. Min Act: -0.1700
Data Index: 4876537 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.3723. Min Act: -0.1700
Data Index: 8625955 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.3723. Min Act: -0.1700
Data Index: 5872952 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.3411. Min Act: -0.1700
Data Index: 7260057 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.3411. Min Act: -0.1700
Data Index: 3483745 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.3411. Min Act: -0.1700
Data Index: 8074213 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.3411. Min Act: -0.1700
Data Index: 3645251 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.3098. Min Act: -0.1700
Data Index: 6519575 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19