Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 35 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.7319. Min Act: -0.1700
Data Index: 8812521 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.7319. Min Act: -0.1700
Data Index: 8062454 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.6537. Min Act: -0.1700
Data Index: 8062453 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.6380. Min Act: -0.1700
Data Index: 2260934 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.6224. Min Act: -0.1700
Data Index: 2930465 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.6224. Min Act: -0.1700
Data Index: 395151 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.6224. Min Act: -0.1700
Data Index: 4520720 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.5598. Min Act: -0.1700
Data Index: 5404155 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.5284. Min Act: -0.1700
Data Index: 577462 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.5441. Min Act: -0.1541
Data Index: 7098501 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.4971. Min Act: -0.1700
Data Index: 6603289 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.5284. Min Act: -0.1700
Data Index: 3824026 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.5284. Min Act: -0.1700
Data Index: 7397341 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.5441. Min Act: -0.1700
Data Index: 526713 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.5284. Min Act: -0.1700
Data Index: 1500597 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.5128. Min Act: -0.1700
Data Index: 4101160 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.5128. Min Act: -0.1700
Data Index: 3978749 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.5128. Min Act: -0.1700
Data Index: 1945111 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.4971. Min Act: -0.1700
Data Index: 2509930 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.4815. Min Act: -0.1700
Data Index: 1664696 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19