Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4791 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2974. Min Range: -7.2974
Max Act: 7.2974. Min Act: -0.1700
Data Index: 6175893 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2974. Min Range: -7.2974
Max Act: 7.2662. Min Act: -0.1700
Data Index: 966885 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2974. Min Range: -7.2974
Max Act: 7.2662. Min Act: -0.1700
Data Index: 6914276 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2974. Min Range: -7.2974
Max Act: 7.0162. Min Act: -0.1700
Data Index: 7541732 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2974. Min Range: -7.2974
Max Act: 6.9537. Min Act: -0.1700
Data Index: 4607332 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2974. Min Range: -7.2974
Max Act: 6.9224. Min Act: -0.1700
Data Index: 7830758 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2974. Min Range: -7.2974
Max Act: 6.8912. Min Act: -0.1700
Data Index: 4582418 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2974. Min Range: -7.2974
Max Act: 6.8599. Min Act: -0.1700
Data Index: 702571 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2974. Min Range: -7.2974
Max Act: 6.7974. Min Act: -0.1700
Data Index: 8462348 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2974. Min Range: -7.2974
Max Act: 6.7662. Min Act: -0.1700
Data Index: 8479453 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2974. Min Range: -7.2974
Max Act: 6.7037. Min Act: -0.1700
Data Index: 1862245 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2974. Min Range: -7.2974
Max Act: 6.7037. Min Act: -0.1700
Data Index: 2157607 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2974. Min Range: -7.2974
Max Act: 6.7037. Min Act: -0.1700
Data Index: 1133118 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2974. Min Range: -7.2974
Max Act: 6.6724. Min Act: -0.1700
Data Index: 2764499 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2974. Min Range: -7.2974
Max Act: 6.6099. Min Act: -0.1700
Data Index: 7796510 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2974. Min Range: -7.2974
Max Act: 6.6412. Min Act: -0.1700
Data Index: 2438750 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2974. Min Range: -7.2974
Max Act: 6.6412. Min Act: -0.1700
Data Index: 6498080 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2974. Min Range: -7.2974
Max Act: 6.6412. Min Act: -0.1700
Data Index: 7080055 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2974. Min Range: -7.2974
Max Act: 6.6099. Min Act: -0.1700
Data Index: 1422139 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2974. Min Range: -7.2974
Max Act: 6.6099. Min Act: -0.1700
Data Index: 593233 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19