Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2503 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3413. Min Range: -4.3413
Max Act: 4.3413. Min Act: -0.1700
Data Index: 5748372 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3413. Min Range: -4.3413
Max Act: 4.2788. Min Act: -0.1700
Data Index: 4701923 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3413. Min Range: -4.3413
Max Act: 4.2476. Min Act: -0.1700
Data Index: 8670114 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3413. Min Range: -4.3413
Max Act: 4.2163. Min Act: -0.1700
Data Index: 613809 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3413. Min Range: -4.3413
Max Act: 4.1851. Min Act: -0.1700
Data Index: 4351882 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3413. Min Range: -4.3413
Max Act: 4.1851. Min Act: -0.1700
Data Index: 1156825 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3413. Min Range: -4.3413
Max Act: 4.1226. Min Act: -0.1700
Data Index: 7421092 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3413. Min Range: -4.3413
Max Act: 4.1226. Min Act: -0.1700
Data Index: 1156824 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3413. Min Range: -4.3413
Max Act: 4.1538. Min Act: -0.1700
Data Index: 1945534 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3413. Min Range: -4.3413
Max Act: 4.0600. Min Act: -0.1700
Data Index: 5749526 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3413. Min Range: -4.3413
Max Act: 4.0913. Min Act: -0.1700
Data Index: 934067 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3413. Min Range: -4.3413
Max Act: 4.0600. Min Act: -0.1700
Data Index: 6863021 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3413. Min Range: -4.3413
Max Act: 4.0600. Min Act: -0.1700
Data Index: 46480 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3413. Min Range: -4.3413
Max Act: 4.0600. Min Act: -0.1700
Data Index: 5523828 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3413. Min Range: -4.3413
Max Act: 4.0600. Min Act: -0.1700
Data Index: 1457042 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3413. Min Range: -4.3413
Max Act: 4.0913. Min Act: -0.1700
Data Index: 3377371 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3413. Min Range: -4.3413
Max Act: 4.0913. Min Act: -0.1700
Data Index: 5886362 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3413. Min Range: -4.3413
Max Act: 4.0600. Min Act: -0.1700
Data Index: 755443 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3413. Min Range: -4.3413
Max Act: 4.0288. Min Act: -0.1700
Data Index: 3372895 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3413. Min Range: -4.3413
Max Act: 4.0288. Min Act: -0.1700
Data Index: 7391685 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19