Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2416 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1992. Min Range: -7.1992
Max Act: 7.1992. Min Act: -0.1700
Data Index: 1719868 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1992. Min Range: -7.1992
Max Act: 7.0429. Min Act: -0.1700
Data Index: 670788 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1992. Min Range: -7.1992
Max Act: 7.0429. Min Act: -0.1700
Data Index: 5247400 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.9179. Min Act: -0.1700
Data Index: 5729405 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.8867. Min Act: -0.1700
Data Index: 3102323 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.7617. Min Act: -0.1700
Data Index: 4358602 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.6992. Min Act: -0.1700
Data Index: 7346286 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.6679. Min Act: -0.1700
Data Index: 8280726 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.6367. Min Act: -0.1700
Data Index: 1069546 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.6367. Min Act: -0.1700
Data Index: 8374879 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.6054. Min Act: -0.1700
Data Index: 4454445 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.6367. Min Act: -0.1700
Data Index: 7202182 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.5742. Min Act: -0.1700
Data Index: 6258055 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.5742. Min Act: -0.1700
Data Index: 4397331 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.5742. Min Act: -0.1700
Data Index: 6704194 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.5742. Min Act: -0.1700
Data Index: 867993 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.5742. Min Act: -0.1700
Data Index: 3040767 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.5429. Min Act: -0.1700
Data Index: 1588150 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.5742. Min Act: -0.1700
Data Index: 4591464 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.4804. Min Act: -0.1700
Data Index: 7013645 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19