Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 756 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.5356. Min Act: -0.1700
Data Index: 1787989 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.3481. Min Act: -0.1700
Data Index: 7388917 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.3169. Min Act: -0.1700
Data Index: 8329034 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.3169. Min Act: -0.1700
Data Index: 3420405 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.3169. Min Act: -0.1700
Data Index: 2627149 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.2856. Min Act: -0.1700
Data Index: 3911402 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.2544. Min Act: -0.1700
Data Index: 8430951 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.2231. Min Act: -0.1700
Data Index: 6177006 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.2544. Min Act: -0.1700
Data Index: 339720 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1919. Min Act: -0.1700
Data Index: 6431630 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.2231. Min Act: -0.1700
Data Index: 2068491 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1606. Min Act: -0.1700
Data Index: 4248140 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1919. Min Act: -0.1700
Data Index: 2239341 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1919. Min Act: -0.1700
Data Index: 7369147 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1606. Min Act: -0.1700
Data Index: 5536167 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1606. Min Act: -0.1700
Data Index: 8695479 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1606. Min Act: -0.1700
Data Index: 4471484 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1606. Min Act: -0.1700
Data Index: 432716 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1294. Min Act: -0.1700
Data Index: 7149093 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1294. Min Act: -0.1700
Data Index: 56374 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19