Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2830 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8490. Min Range: -3.8490
Max Act: 3.8177. Min Act: -0.1700
Data Index: 6399332 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8490. Min Range: -3.8490
Max Act: 3.8490. Min Act: -0.1700
Data Index: 5809754 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8490. Min Range: -3.8490
Max Act: 3.8490. Min Act: -0.1700
Data Index: 5272448 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8490. Min Range: -3.8490
Max Act: 3.8177. Min Act: -0.1700
Data Index: 3980474 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8490. Min Range: -3.8490
Max Act: 3.8490. Min Act: -0.1700
Data Index: 2918952 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8490. Min Range: -3.8490
Max Act: 3.8177. Min Act: -0.1700
Data Index: 1288793 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8490. Min Range: -3.8490
Max Act: 3.7865. Min Act: -0.1700
Data Index: 706019 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8490. Min Range: -3.8490
Max Act: 3.7865. Min Act: -0.1700
Data Index: 800655 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8490. Min Range: -3.8490
Max Act: 3.7865. Min Act: -0.1700
Data Index: 7351836 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8490. Min Range: -3.8490
Max Act: 3.7552. Min Act: -0.1700
Data Index: 493330 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8490. Min Range: -3.8490
Max Act: 3.7552. Min Act: -0.1700
Data Index: 4742367 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8490. Min Range: -3.8490
Max Act: 3.7552. Min Act: -0.1700
Data Index: 7249877 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8490. Min Range: -3.8490
Max Act: 3.7239. Min Act: -0.1700
Data Index: 3441204 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8490. Min Range: -3.8490
Max Act: 3.7239. Min Act: -0.1700
Data Index: 3919466 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8490. Min Range: -3.8490
Max Act: 3.7239. Min Act: -0.1700
Data Index: 4578133 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8490. Min Range: -3.8490
Max Act: 3.7239. Min Act: -0.1700
Data Index: 773464 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8490. Min Range: -3.8490
Max Act: 3.7239. Min Act: -0.1700
Data Index: 4742365 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8490. Min Range: -3.8490
Max Act: 3.7239. Min Act: -0.1700
Data Index: 2395786 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8490. Min Range: -3.8490
Max Act: 3.7239. Min Act: -0.1700
Data Index: 6063862 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8490. Min Range: -3.8490
Max Act: 3.7239. Min Act: -0.1700
Data Index: 6358286 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19