Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5438 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9270. Min Range: -10.9270
Max Act: 10.9270. Min Act: -0.1700
Data Index: 7215187 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9270. Min Range: -10.9270
Max Act: 10.6770. Min Act: -0.1700
Data Index: 775492 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9270. Min Range: -10.9270
Max Act: 10.0520. Min Act: -0.1700
Data Index: 8430098 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9270. Min Range: -10.9270
Max Act: 9.8645. Min Act: -0.1700
Data Index: 695496 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9270. Min Range: -10.9270
Max Act: 9.8645. Min Act: -0.1700
Data Index: 7294319 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9270. Min Range: -10.9270
Max Act: 9.8645. Min Act: -0.1700
Data Index: 7309121 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9270. Min Range: -10.9270
Max Act: 9.8645. Min Act: -0.1700
Data Index: 5391976 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9270. Min Range: -10.9270
Max Act: 9.8020. Min Act: -0.1700
Data Index: 6484004 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9270. Min Range: -10.9270
Max Act: 9.8020. Min Act: -0.1700
Data Index: 553616 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9270. Min Range: -10.9270
Max Act: 9.8020. Min Act: -0.1700
Data Index: 7900051 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9270. Min Range: -10.9270
Max Act: 9.7395. Min Act: -0.1700
Data Index: 6168021 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9270. Min Range: -10.9270
Max Act: 9.7395. Min Act: -0.1700
Data Index: 2252012 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9270. Min Range: -10.9270
Max Act: 9.6770. Min Act: -0.1700
Data Index: 8743760 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9270. Min Range: -10.9270
Max Act: 9.7395. Min Act: -0.1700
Data Index: 3333473 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9270. Min Range: -10.9270
Max Act: 9.6145. Min Act: -0.1700
Data Index: 5176946 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9270. Min Range: -10.9270
Max Act: 9.6145. Min Act: -0.1700
Data Index: 6929390 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9270. Min Range: -10.9270
Max Act: 9.6145. Min Act: -0.1700
Data Index: 8428911 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9270. Min Range: -10.9270
Max Act: 9.6145. Min Act: -0.1700
Data Index: 1662597 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9270. Min Range: -10.9270
Max Act: 9.5520. Min Act: -0.1700
Data Index: 1438478 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9270. Min Range: -10.9270
Max Act: 9.5520. Min Act: -0.1700
Data Index: 6101748 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19