Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3335 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8316. Min Range: -6.8316
Max Act: 6.8316. Min Act: -0.1700
Data Index: 6315522 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8316. Min Range: -6.8316
Max Act: 6.6753. Min Act: -0.1700
Data Index: 908887 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8316. Min Range: -6.8316
Max Act: 6.6128. Min Act: -0.1700
Data Index: 8469052 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8316. Min Range: -6.8316
Max Act: 6.5816. Min Act: -0.1700
Data Index: 4079403 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8316. Min Range: -6.8316
Max Act: 6.5816. Min Act: -0.1700
Data Index: 355956 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8316. Min Range: -6.8316
Max Act: 6.5503. Min Act: -0.1700
Data Index: 3059901 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8316. Min Range: -6.8316
Max Act: 6.5503. Min Act: -0.1700
Data Index: 6518096 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8316. Min Range: -6.8316
Max Act: 6.5503. Min Act: -0.1700
Data Index: 7254702 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8316. Min Range: -6.8316
Max Act: 6.5503. Min Act: -0.1700
Data Index: 2387638 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8316. Min Range: -6.8316
Max Act: 6.5191. Min Act: -0.1700
Data Index: 4288057 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8316. Min Range: -6.8316
Max Act: 6.5503. Min Act: -0.1700
Data Index: 8369899 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8316. Min Range: -6.8316
Max Act: 6.4878. Min Act: -0.1700
Data Index: 4079402 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8316. Min Range: -6.8316
Max Act: 6.4566. Min Act: -0.1700
Data Index: 1439115 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8316. Min Range: -6.8316
Max Act: 6.4566. Min Act: -0.1700
Data Index: 8677450 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8316. Min Range: -6.8316
Max Act: 6.4566. Min Act: -0.1700
Data Index: 6585696 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8316. Min Range: -6.8316
Max Act: 6.4253. Min Act: -0.1700
Data Index: 289055 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8316. Min Range: -6.8316
Max Act: 6.4253. Min Act: -0.1700
Data Index: 5299355 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8316. Min Range: -6.8316
Max Act: 6.3941. Min Act: -0.1700
Data Index: 5386251 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8316. Min Range: -6.8316
Max Act: 6.3941. Min Act: -0.1700
Data Index: 51021 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8316. Min Range: -6.8316
Max Act: 6.3628. Min Act: -0.1700
Data Index: 3994447 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19