Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2480 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9587. Min Range: -1.9587
Max Act: 1.9587. Min Act: -0.1699
Data Index: 5914051 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9587. Min Range: -1.9587
Max Act: 1.8393. Min Act: -0.1700
Data Index: 5837750 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9587. Min Range: -1.9587
Max Act: 1.8393. Min Act: -0.1700
Data Index: 8279531 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9587. Min Range: -1.9587
Max Act: 1.8050. Min Act: -0.1700
Data Index: 8031814 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9587. Min Range: -1.9587
Max Act: 1.8050. Min Act: -0.1700
Data Index: 662946 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9587. Min Range: -1.9587
Max Act: 1.7878. Min Act: -0.1698
Data Index: 1709976 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9587. Min Range: -1.9587
Max Act: 1.8050. Min Act: -0.1700
Data Index: 1542320 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9587. Min Range: -1.9587
Max Act: 1.7706. Min Act: -0.1700
Data Index: 3301300 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9587. Min Range: -1.9587
Max Act: 1.7878. Min Act: -0.1684
Data Index: 2491503 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9587. Min Range: -1.9587
Max Act: 1.7706. Min Act: -0.1692
Data Index: 454829 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9587. Min Range: -1.9587
Max Act: 1.7533. Min Act: -0.1691
Data Index: 6011170 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9587. Min Range: -1.9587
Max Act: 1.7360. Min Act: -0.1700
Data Index: 4668017 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9587. Min Range: -1.9587
Max Act: 1.7187. Min Act: -0.1700
Data Index: 7273980 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9587. Min Range: -1.9587
Max Act: 1.7014. Min Act: -0.1690
Data Index: 7163124 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9587. Min Range: -1.9587
Max Act: 1.7014. Min Act: -0.1700
Data Index: 5222845 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9587. Min Range: -1.9587
Max Act: 1.6840. Min Act: -0.1700
Data Index: 1159436 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9587. Min Range: -1.9587
Max Act: 1.6667. Min Act: -0.1700
Data Index: 4786320 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9587. Min Range: -1.9587
Max Act: 1.6318. Min Act: -0.1699
Data Index: 6864949 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9587. Min Range: -1.9587
Max Act: 1.6667. Min Act: -0.1700
Data Index: 8514025 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9587. Min Range: -1.9587
Max Act: 1.6493. Min Act: -0.1698
Data Index: 3660801 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19