Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3856 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1520. Min Range: -8.1520
Max Act: 8.1520. Min Act: -0.1700
Data Index: 2843814 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1520. Min Range: -8.1520
Max Act: 7.1832. Min Act: -0.1700
Data Index: 5413913 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1520. Min Range: -8.1520
Max Act: 6.9020. Min Act: -0.1700
Data Index: 2841583 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1520. Min Range: -8.1520
Max Act: 6.6520. Min Act: -0.1700
Data Index: 1445214 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1520. Min Range: -8.1520
Max Act: 6.6520. Min Act: -0.1700
Data Index: 2803014 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1520. Min Range: -8.1520
Max Act: 6.5270. Min Act: -0.1700
Data Index: 4472615 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1520. Min Range: -8.1520
Max Act: 6.5582. Min Act: -0.1700
Data Index: 2364501 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1520. Min Range: -8.1520
Max Act: 6.4957. Min Act: -0.1700
Data Index: 1310195 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1520. Min Range: -8.1520
Max Act: 6.4645. Min Act: -0.1700
Data Index: 7293159 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1520. Min Range: -8.1520
Max Act: 6.4645. Min Act: -0.1700
Data Index: 8378564 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1520. Min Range: -8.1520
Max Act: 6.4020. Min Act: -0.1700
Data Index: 7992466 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1520. Min Range: -8.1520
Max Act: 6.4020. Min Act: -0.1700
Data Index: 795659 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1520. Min Range: -8.1520
Max Act: 6.3707. Min Act: -0.1700
Data Index: 2287442 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1520. Min Range: -8.1520
Max Act: 6.3395. Min Act: -0.1700
Data Index: 1770483 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1520. Min Range: -8.1520
Max Act: 6.2770. Min Act: -0.1700
Data Index: 6330578 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1520. Min Range: -8.1520
Max Act: 6.2770. Min Act: -0.1700
Data Index: 4349152 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1520. Min Range: -8.1520
Max Act: 6.2457. Min Act: -0.1700
Data Index: 5289037 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1520. Min Range: -8.1520
Max Act: 6.2457. Min Act: -0.1700
Data Index: 1660612 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1520. Min Range: -8.1520
Max Act: 6.2457. Min Act: -0.1700
Data Index: 4330690 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1520. Min Range: -8.1520
Max Act: 6.2457. Min Act: -0.1700
Data Index: 732502 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19