Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2059 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2274. Min Range: -2.2274
Max Act: 2.2274. Min Act: -0.1697
Data Index: 4153063 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2274. Min Range: -2.2274
Max Act: 2.2108. Min Act: -0.1700
Data Index: 7979763 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2274. Min Range: -2.2274
Max Act: 2.2274. Min Act: -0.1700
Data Index: 4905746 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2274. Min Range: -2.2274
Max Act: 2.1942. Min Act: -0.1700
Data Index: 5745799 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2274. Min Range: -2.2274
Max Act: 2.1776. Min Act: -0.1700
Data Index: 8774790 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2274. Min Range: -2.2274
Max Act: 2.1776. Min Act: -0.1700
Data Index: 1033953 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2274. Min Range: -2.2274
Max Act: 2.1776. Min Act: -0.1700
Data Index: 6115811 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2274. Min Range: -2.2274
Max Act: 2.1610. Min Act: -0.1700
Data Index: 6631450 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2274. Min Range: -2.2274
Max Act: 2.1443. Min Act: -0.1700
Data Index: 5881935 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2274. Min Range: -2.2274
Max Act: 2.1443. Min Act: -0.1700
Data Index: 1372284 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2274. Min Range: -2.2274
Max Act: 2.1443. Min Act: -0.1700
Data Index: 8271740 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2274. Min Range: -2.2274
Max Act: 2.1443. Min Act: -0.1700
Data Index: 8807350 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2274. Min Range: -2.2274
Max Act: 2.1443. Min Act: -0.1700
Data Index: 2548807 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2274. Min Range: -2.2274
Max Act: 2.1443. Min Act: -0.1700
Data Index: 7712583 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2274. Min Range: -2.2274
Max Act: 2.1276. Min Act: -0.1700
Data Index: 4134442 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2274. Min Range: -2.2274
Max Act: 2.1276. Min Act: -0.1700
Data Index: 1405216 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2274. Min Range: -2.2274
Max Act: 2.1276. Min Act: -0.1700
Data Index: 3652723 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2274. Min Range: -2.2274
Max Act: 2.1109. Min Act: -0.1700
Data Index: 525679 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2274. Min Range: -2.2274
Max Act: 2.1276. Min Act: -0.1700
Data Index: 6279815 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2274. Min Range: -2.2274
Max Act: 2.1276. Min Act: -0.1700
Data Index: 6625531 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19