Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5479 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5135. Min Range: -3.5135
Max Act: 3.5135. Min Act: -0.1700
Data Index: 2774484 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5135. Min Range: -3.5135
Max Act: 3.4665. Min Act: -0.1700
Data Index: 1018071 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5135. Min Range: -3.5135
Max Act: 3.4508. Min Act: -0.1700
Data Index: 6183763 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5135. Min Range: -3.5135
Max Act: 3.4665. Min Act: -0.1700
Data Index: 2209423 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5135. Min Range: -3.5135
Max Act: 3.4508. Min Act: -0.1700
Data Index: 8475436 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5135. Min Range: -3.5135
Max Act: 3.4195. Min Act: -0.1700
Data Index: 1088002 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5135. Min Range: -3.5135
Max Act: 3.4038. Min Act: -0.1700
Data Index: 1011301 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5135. Min Range: -3.5135
Max Act: 3.3881. Min Act: -0.1700
Data Index: 4896199 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5135. Min Range: -3.5135
Max Act: 3.4038. Min Act: -0.1700
Data Index: 218643 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5135. Min Range: -3.5135
Max Act: 3.3568. Min Act: -0.1700
Data Index: 8111697 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5135. Min Range: -3.5135
Max Act: 3.3254. Min Act: -0.1700
Data Index: 5838654 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5135. Min Range: -3.5135
Max Act: 3.3411. Min Act: -0.1700
Data Index: 5219960 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5135. Min Range: -3.5135
Max Act: 3.3411. Min Act: -0.1700
Data Index: 6280771 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5135. Min Range: -3.5135
Max Act: 3.3411. Min Act: -0.1700
Data Index: 291311 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5135. Min Range: -3.5135
Max Act: 3.3254. Min Act: -0.1700
Data Index: 2757101 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5135. Min Range: -3.5135
Max Act: 3.3097. Min Act: -0.1700
Data Index: 8341242 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5135. Min Range: -3.5135
Max Act: 3.3254. Min Act: -0.1700
Data Index: 7287535 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5135. Min Range: -3.5135
Max Act: 3.2940. Min Act: -0.1700
Data Index: 3841957 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5135. Min Range: -3.5135
Max Act: 3.2940. Min Act: -0.1700
Data Index: 1454093 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5135. Min Range: -3.5135
Max Act: 3.2940. Min Act: -0.1700
Data Index: 8253768 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19