Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3200 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5378. Min Range: -7.5378
Max Act: 7.5378. Min Act: -0.1700
Data Index: 4862692 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5378. Min Range: -7.5378
Max Act: 7.4128. Min Act: -0.1700
Data Index: 4596474 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5378. Min Range: -7.5378
Max Act: 7.2565. Min Act: -0.1700
Data Index: 1511033 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5378. Min Range: -7.5378
Max Act: 7.2878. Min Act: -0.1700
Data Index: 193682 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5378. Min Range: -7.5378
Max Act: 7.2878. Min Act: -0.1700
Data Index: 6850421 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5378. Min Range: -7.5378
Max Act: 7.2878. Min Act: -0.1700
Data Index: 8675269 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5378. Min Range: -7.5378
Max Act: 7.2565. Min Act: -0.1700
Data Index: 5212035 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5378. Min Range: -7.5378
Max Act: 7.2565. Min Act: -0.1700
Data Index: 1069655 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5378. Min Range: -7.5378
Max Act: 7.2253. Min Act: -0.1700
Data Index: 8301972 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5378. Min Range: -7.5378
Max Act: 7.1940. Min Act: -0.1700
Data Index: 7732149 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5378. Min Range: -7.5378
Max Act: 7.1940. Min Act: -0.1700
Data Index: 165785 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5378. Min Range: -7.5378
Max Act: 7.1940. Min Act: -0.1700
Data Index: 3541816 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5378. Min Range: -7.5378
Max Act: 7.1628. Min Act: -0.1700
Data Index: 7423768 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5378. Min Range: -7.5378
Max Act: 7.1315. Min Act: -0.1700
Data Index: 1150819 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5378. Min Range: -7.5378
Max Act: 7.1315. Min Act: -0.1700
Data Index: 5519221 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5378. Min Range: -7.5378
Max Act: 7.1628. Min Act: -0.1700
Data Index: 4545113 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5378. Min Range: -7.5378
Max Act: 7.1628. Min Act: -0.1700
Data Index: 964172 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5378. Min Range: -7.5378
Max Act: 7.1628. Min Act: -0.1700
Data Index: 8505958 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5378. Min Range: -7.5378
Max Act: 7.1315. Min Act: -0.1700
Data Index: 8348539 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5378. Min Range: -7.5378
Max Act: 7.1315. Min Act: -0.1700
Data Index: 1752253 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19