Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2255 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8404. Min Range: -6.8404
Max Act: 6.8404. Min Act: -0.1700
Data Index: 2482876 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8404. Min Range: -6.8404
Max Act: 6.7779. Min Act: -0.1700
Data Index: 3004117 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8404. Min Range: -6.8404
Max Act: 6.7467. Min Act: -0.1700
Data Index: 2394148 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8404. Min Range: -6.8404
Max Act: 6.5904. Min Act: -0.1700
Data Index: 5852272 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8404. Min Range: -6.8404
Max Act: 6.5592. Min Act: -0.1700
Data Index: 2549108 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8404. Min Range: -6.8404
Max Act: 6.4342. Min Act: -0.1700
Data Index: 2731382 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8404. Min Range: -6.8404
Max Act: 6.4342. Min Act: -0.1700
Data Index: 8729307 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8404. Min Range: -6.8404
Max Act: 6.4342. Min Act: -0.1700
Data Index: 8797636 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8404. Min Range: -6.8404
Max Act: 6.4029. Min Act: -0.1700
Data Index: 230227 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8404. Min Range: -6.8404
Max Act: 6.3717. Min Act: -0.1700
Data Index: 6408242 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8404. Min Range: -6.8404
Max Act: 6.3717. Min Act: -0.1700
Data Index: 1869963 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8404. Min Range: -6.8404
Max Act: 6.3404. Min Act: -0.1700
Data Index: 1467548 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8404. Min Range: -6.8404
Max Act: 6.2779. Min Act: -0.1700
Data Index: 5328289 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8404. Min Range: -6.8404
Max Act: 6.3092. Min Act: -0.1700
Data Index: 4082247 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8404. Min Range: -6.8404
Max Act: 6.3092. Min Act: -0.1700
Data Index: 4014429 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8404. Min Range: -6.8404
Max Act: 6.3092. Min Act: -0.1700
Data Index: 1148722 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8404. Min Range: -6.8404
Max Act: 6.3092. Min Act: -0.1700
Data Index: 3435089 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8404. Min Range: -6.8404
Max Act: 6.2779. Min Act: -0.1700
Data Index: 6506165 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8404. Min Range: -6.8404
Max Act: 6.2779. Min Act: -0.1700
Data Index: 7558419 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8404. Min Range: -6.8404
Max Act: 6.3092. Min Act: -0.1700
Data Index: 4959988 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19