Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1137 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6696. Min Range: -9.6696
Max Act: 9.6696. Min Act: -0.1700
Data Index: 6569352 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6696. Min Range: -9.6696
Max Act: 8.9821. Min Act: -0.1700
Data Index: 4060127 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6696. Min Range: -9.6696
Max Act: 8.8571. Min Act: -0.1700
Data Index: 5298431 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6696. Min Range: -9.6696
Max Act: 8.8571. Min Act: -0.1700
Data Index: 45797 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6696. Min Range: -9.6696
Max Act: 8.6696. Min Act: -0.1700
Data Index: 3488225 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6696. Min Range: -9.6696
Max Act: 8.6071. Min Act: -0.1700
Data Index: 4127332 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6696. Min Range: -9.6696
Max Act: 8.6696. Min Act: -0.1700
Data Index: 4043721 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6696. Min Range: -9.6696
Max Act: 8.6071. Min Act: -0.1700
Data Index: 7323559 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6696. Min Range: -9.6696
Max Act: 8.5446. Min Act: -0.1700
Data Index: 2961277 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6696. Min Range: -9.6696
Max Act: 8.4821. Min Act: -0.1700
Data Index: 6891310 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6696. Min Range: -9.6696
Max Act: 8.4821. Min Act: -0.1700
Data Index: 134415 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6696. Min Range: -9.6696
Max Act: 8.5446. Min Act: -0.1700
Data Index: 1128280 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6696. Min Range: -9.6696
Max Act: 8.4821. Min Act: -0.1700
Data Index: 3513346 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6696. Min Range: -9.6696
Max Act: 8.4196. Min Act: -0.1700
Data Index: 8029693 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6696. Min Range: -9.6696
Max Act: 8.4196. Min Act: -0.1700
Data Index: 208668 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6696. Min Range: -9.6696
Max Act: 8.4196. Min Act: -0.1700
Data Index: 8039630 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6696. Min Range: -9.6696
Max Act: 8.3571. Min Act: -0.1700
Data Index: 5940019 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6696. Min Range: -9.6696
Max Act: 8.2946. Min Act: -0.1700
Data Index: 1492867 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6696. Min Range: -9.6696
Max Act: 8.3571. Min Act: -0.1700
Data Index: 4059058 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6696. Min Range: -9.6696
Max Act: 8.3571. Min Act: -0.1700
Data Index: 8832932 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19