Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3740 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8383. Min Range: -2.8383
Max Act: 2.8383. Min Act: -0.1700
Data Index: 4729291 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8383. Min Range: -2.8383
Max Act: 2.8065. Min Act: -0.1700
Data Index: 4953641 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8383. Min Range: -2.8383
Max Act: 2.7906. Min Act: -0.1700
Data Index: 5809877 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8383. Min Range: -2.8383
Max Act: 2.7906. Min Act: -0.1700
Data Index: 2484281 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8383. Min Range: -2.8383
Max Act: 2.7746. Min Act: -0.1700
Data Index: 8114855 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8383. Min Range: -2.8383
Max Act: 2.7587. Min Act: -0.1700
Data Index: 3368389 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8383. Min Range: -2.8383
Max Act: 2.7427. Min Act: -0.1700
Data Index: 8241608 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8383. Min Range: -2.8383
Max Act: 2.7587. Min Act: -0.1700
Data Index: 7447104 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8383. Min Range: -2.8383
Max Act: 2.7587. Min Act: -0.1700
Data Index: 5644242 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8383. Min Range: -2.8383
Max Act: 2.7427. Min Act: -0.1700
Data Index: 3956495 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8383. Min Range: -2.8383
Max Act: 2.7587. Min Act: -0.1700
Data Index: 5491532 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8383. Min Range: -2.8383
Max Act: 2.7587. Min Act: -0.1700
Data Index: 2679161 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8383. Min Range: -2.8383
Max Act: 2.7427. Min Act: -0.1700
Data Index: 7590768 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8383. Min Range: -2.8383
Max Act: 2.7267. Min Act: -0.1700
Data Index: 534177 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8383. Min Range: -2.8383
Max Act: 2.7427. Min Act: -0.1700
Data Index: 3198763 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8383. Min Range: -2.8383
Max Act: 2.7427. Min Act: -0.1700
Data Index: 6655760 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8383. Min Range: -2.8383
Max Act: 2.7427. Min Act: -0.1700
Data Index: 6296944 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8383. Min Range: -2.8383
Max Act: 2.7427. Min Act: -0.1700
Data Index: 2218598 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8383. Min Range: -2.8383
Max Act: 2.7267. Min Act: -0.1700
Data Index: 41588 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8383. Min Range: -2.8383
Max Act: 2.7267. Min Act: -0.1700
Data Index: 5833581 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19