Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2735 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4415. Min Range: -7.4415
Max Act: 7.4415. Min Act: -0.1700
Data Index: 6006546 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4415. Min Range: -7.4415
Max Act: 7.4103. Min Act: -0.1700
Data Index: 7599614 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4415. Min Range: -7.4415
Max Act: 7.4103. Min Act: -0.1700
Data Index: 3792424 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4415. Min Range: -7.4415
Max Act: 7.4103. Min Act: -0.1700
Data Index: 487473 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4415. Min Range: -7.4415
Max Act: 7.3790. Min Act: -0.1700
Data Index: 284555 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4415. Min Range: -7.4415
Max Act: 7.3790. Min Act: -0.1700
Data Index: 2315044 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4415. Min Range: -7.4415
Max Act: 7.3478. Min Act: -0.1700
Data Index: 8574727 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4415. Min Range: -7.4415
Max Act: 7.2540. Min Act: -0.1700
Data Index: 4999798 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4415. Min Range: -7.4415
Max Act: 7.2540. Min Act: -0.1700
Data Index: 6716339 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4415. Min Range: -7.4415
Max Act: 7.2228. Min Act: -0.1700
Data Index: 650017 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4415. Min Range: -7.4415
Max Act: 7.2228. Min Act: -0.1700
Data Index: 4934511 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4415. Min Range: -7.4415
Max Act: 7.1915. Min Act: -0.1700
Data Index: 285224 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4415. Min Range: -7.4415
Max Act: 7.1915. Min Act: -0.1700
Data Index: 2775117 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4415. Min Range: -7.4415
Max Act: 7.1915. Min Act: -0.1700
Data Index: 8753817 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4415. Min Range: -7.4415
Max Act: 7.1603. Min Act: -0.1700
Data Index: 82668 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4415. Min Range: -7.4415
Max Act: 7.1603. Min Act: -0.1700
Data Index: 3716931 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4415. Min Range: -7.4415
Max Act: 7.1290. Min Act: -0.1700
Data Index: 3259612 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4415. Min Range: -7.4415
Max Act: 7.1290. Min Act: -0.1700
Data Index: 3038064 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4415. Min Range: -7.4415
Max Act: 7.1603. Min Act: -0.1700
Data Index: 40518 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4415. Min Range: -7.4415
Max Act: 7.1603. Min Act: -0.1700
Data Index: 4678895 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19