Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3957 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2156. Min Range: -7.2156
Max Act: 7.2156. Min Act: -0.1700
Data Index: 4372017 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2156. Min Range: -7.2156
Max Act: 7.0906. Min Act: -0.1700
Data Index: 4130115 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2156. Min Range: -7.2156
Max Act: 7.0281. Min Act: -0.1700
Data Index: 6552344 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2156. Min Range: -7.2156
Max Act: 7.0593. Min Act: -0.1700
Data Index: 4577510 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.9343. Min Act: -0.1700
Data Index: 6901823 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.8406. Min Act: -0.1700
Data Index: 8389526 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.7468. Min Act: -0.1700
Data Index: 6412194 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.7468. Min Act: -0.1700
Data Index: 859412 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.7468. Min Act: -0.1700
Data Index: 6712271 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.7468. Min Act: -0.1700
Data Index: 3185257 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.7156. Min Act: -0.1700
Data Index: 6249511 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.7156. Min Act: -0.1700
Data Index: 5270269 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.6531. Min Act: -0.1700
Data Index: 4149258 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.6843. Min Act: -0.1700
Data Index: 6739111 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.6531. Min Act: -0.1700
Data Index: 1823035 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.6531. Min Act: -0.1700
Data Index: 8588257 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.6531. Min Act: -0.1700
Data Index: 4967322 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.6531. Min Act: -0.1700
Data Index: 8294978 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.6218. Min Act: -0.1700
Data Index: 5399880 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.6218. Min Act: -0.1700
Data Index: 7948471 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19