Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2179 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2687. Min Range: -3.2687
Max Act: 3.2687. Min Act: -0.1700
Data Index: 6445746 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2687. Min Range: -3.2687
Max Act: 3.1744. Min Act: -0.1700
Data Index: 6445743 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2687. Min Range: -3.2687
Max Act: 3.1744. Min Act: -0.1700
Data Index: 6445745 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2687. Min Range: -3.2687
Max Act: 3.1744. Min Act: -0.1700
Data Index: 8596893 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2687. Min Range: -3.2687
Max Act: 3.1586. Min Act: -0.1700
Data Index: 1697146 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2687. Min Range: -3.2687
Max Act: 3.1429. Min Act: -0.1700
Data Index: 5435135 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2687. Min Range: -3.2687
Max Act: 3.1429. Min Act: -0.1700
Data Index: 5851128 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2687. Min Range: -3.2687
Max Act: 3.1429. Min Act: -0.1700
Data Index: 2376747 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2687. Min Range: -3.2687
Max Act: 3.1429. Min Act: -0.1700
Data Index: 974997 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2687. Min Range: -3.2687
Max Act: 3.1271. Min Act: -0.1700
Data Index: 8490189 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2687. Min Range: -3.2687
Max Act: 3.1271. Min Act: -0.1700
Data Index: 1213455 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2687. Min Range: -3.2687
Max Act: 3.1271. Min Act: -0.1700
Data Index: 2606854 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2687. Min Range: -3.2687
Max Act: 3.1271. Min Act: -0.1700
Data Index: 5255435 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2687. Min Range: -3.2687
Max Act: 3.1271. Min Act: -0.1700
Data Index: 7428963 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2687. Min Range: -3.2687
Max Act: 3.1271. Min Act: -0.1700
Data Index: 4156776 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2687. Min Range: -3.2687
Max Act: 3.1271. Min Act: -0.1700
Data Index: 3312570 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2687. Min Range: -3.2687
Max Act: 3.1114. Min Act: -0.1700
Data Index: 4448419 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2687. Min Range: -3.2687
Max Act: 3.1114. Min Act: -0.1700
Data Index: 4544232 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2687. Min Range: -3.2687
Max Act: 3.1114. Min Act: -0.1700
Data Index: 377359 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2687. Min Range: -3.2687
Max Act: 3.1114. Min Act: -0.1700
Data Index: 572636 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19