Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.8469. Min Act: -0.1700
Data Index: 6030093 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.2219. Min Act: -0.1700
Data Index: 5638051 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.2219. Min Act: -0.1700
Data Index: 4377410 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.1906. Min Act: -0.1700
Data Index: 8733923 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.1594. Min Act: -0.1700
Data Index: 3924440 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.1594. Min Act: -0.1700
Data Index: 3102245 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.1281. Min Act: -0.1700
Data Index: 2931418 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.0969. Min Act: -0.1700
Data Index: 4820998 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.0969. Min Act: -0.1700
Data Index: 2377919 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.0969. Min Act: -0.1700
Data Index: 3358496 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.0656. Min Act: -0.1700
Data Index: 6569888 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.0969. Min Act: -0.1700
Data Index: 4989964 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.0656. Min Act: -0.1700
Data Index: 527983 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.0344. Min Act: -0.1700
Data Index: 4151425 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.0344. Min Act: -0.1700
Data Index: 7802705 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.0031. Min Act: -0.1700
Data Index: 6385995 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.0344. Min Act: -0.1700
Data Index: 2048440 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.0344. Min Act: -0.1700
Data Index: 6151892 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.0344. Min Act: -0.1700
Data Index: 1984042 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.0344. Min Act: -0.1700
Data Index: 6476010 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19