Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3602 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1418. Min Range: -5.1418
Max Act: 5.1418. Min Act: -0.1700
Data Index: 7165674 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1418. Min Range: -5.1418
Max Act: 4.9231. Min Act: -0.1700
Data Index: 7172305 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1418. Min Range: -5.1418
Max Act: 4.9231. Min Act: -0.1700
Data Index: 1482231 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1418. Min Range: -5.1418
Max Act: 4.8606. Min Act: -0.1700
Data Index: 1645398 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1418. Min Range: -5.1418
Max Act: 4.7981. Min Act: -0.1700
Data Index: 8017929 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1418. Min Range: -5.1418
Max Act: 4.7668. Min Act: -0.1700
Data Index: 1534861 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1418. Min Range: -5.1418
Max Act: 4.7668. Min Act: -0.1700
Data Index: 5476735 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1418. Min Range: -5.1418
Max Act: 4.7356. Min Act: -0.1700
Data Index: 869427 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1418. Min Range: -5.1418
Max Act: 4.6731. Min Act: -0.1700
Data Index: 390452 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1418. Min Range: -5.1418
Max Act: 4.7043. Min Act: -0.1700
Data Index: 921696 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1418. Min Range: -5.1418
Max Act: 4.7356. Min Act: -0.1700
Data Index: 1090987 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1418. Min Range: -5.1418
Max Act: 4.6418. Min Act: -0.1700
Data Index: 88050 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1418. Min Range: -5.1418
Max Act: 4.6418. Min Act: -0.1700
Data Index: 4306405 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1418. Min Range: -5.1418
Max Act: 4.6731. Min Act: -0.1700
Data Index: 7735779 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1418. Min Range: -5.1418
Max Act: 4.6731. Min Act: -0.1700
Data Index: 6375272 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1418. Min Range: -5.1418
Max Act: 4.6731. Min Act: -0.1700
Data Index: 449472 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1418. Min Range: -5.1418
Max Act: 4.6418. Min Act: -0.1700
Data Index: 7277727 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1418. Min Range: -5.1418
Max Act: 4.6731. Min Act: -0.1700
Data Index: 3879306 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1418. Min Range: -5.1418
Max Act: 4.6418. Min Act: -0.1700
Data Index: 4086756 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1418. Min Range: -5.1418
Max Act: 4.6418. Min Act: -0.1700
Data Index: 4823706 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19