Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5526 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5970. Min Range: -3.5970
Max Act: 3.5970. Min Act: -0.1700
Data Index: 3592550 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5970. Min Range: -3.5970
Max Act: 3.5970. Min Act: -0.1700
Data Index: 3592566 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5970. Min Range: -3.5970
Max Act: 3.5970. Min Act: -0.1700
Data Index: 8287768 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5970. Min Range: -3.5970
Max Act: 3.5343. Min Act: -0.1700
Data Index: 5549589 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5970. Min Range: -3.5970
Max Act: 3.5030. Min Act: -0.1700
Data Index: 6807366 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5970. Min Range: -3.5970
Max Act: 3.4247. Min Act: -0.1700
Data Index: 4221457 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5970. Min Range: -3.5970
Max Act: 3.4090. Min Act: -0.1700
Data Index: 8693681 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5970. Min Range: -3.5970
Max Act: 3.4090. Min Act: -0.1700
Data Index: 7806866 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5970. Min Range: -3.5970
Max Act: 3.3933. Min Act: -0.1700
Data Index: 3592547 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5970. Min Range: -3.5970
Max Act: 3.3776. Min Act: -0.1700
Data Index: 3550076 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5970. Min Range: -3.5970
Max Act: 3.3620. Min Act: -0.1700
Data Index: 827768 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5970. Min Range: -3.5970
Max Act: 3.3463. Min Act: -0.1700
Data Index: 166643 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5970. Min Range: -3.5970
Max Act: 3.3463. Min Act: -0.1700
Data Index: 8779819 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5970. Min Range: -3.5970
Max Act: 3.3306. Min Act: -0.1700
Data Index: 8779822 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5970. Min Range: -3.5970
Max Act: 3.2992. Min Act: -0.1700
Data Index: 8203595 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5970. Min Range: -3.5970
Max Act: 3.2521. Min Act: -0.1700
Data Index: 8818317 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5970. Min Range: -3.5970
Max Act: 3.2521. Min Act: -0.1700
Data Index: 2758430 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5970. Min Range: -3.5970
Max Act: 3.2206. Min Act: -0.1700
Data Index: 215471 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5970. Min Range: -3.5970
Max Act: 3.2364. Min Act: -0.1700
Data Index: 4596848 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5970. Min Range: -3.5970
Max Act: 3.2521. Min Act: -0.1700
Data Index: 4349696 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19