Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2819 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7383. Min Range: -5.7383
Max Act: 5.7383. Min Act: -0.1700
Data Index: 5785564 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7383. Min Range: -5.7383
Max Act: 5.6758. Min Act: -0.1700
Data Index: 4709466 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7383. Min Range: -5.7383
Max Act: 5.6758. Min Act: -0.1700
Data Index: 4386724 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7383. Min Range: -5.7383
Max Act: 5.6133. Min Act: -0.1700
Data Index: 522835 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7383. Min Range: -5.7383
Max Act: 5.6133. Min Act: -0.1700
Data Index: 4476728 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7383. Min Range: -5.7383
Max Act: 5.5508. Min Act: -0.1700
Data Index: 857554 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7383. Min Range: -5.7383
Max Act: 5.5508. Min Act: -0.1700
Data Index: 8645858 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7383. Min Range: -5.7383
Max Act: 5.5508. Min Act: -0.1700
Data Index: 5785571 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7383. Min Range: -5.7383
Max Act: 5.5195. Min Act: -0.1700
Data Index: 5961097 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7383. Min Range: -5.7383
Max Act: 5.5508. Min Act: -0.1700
Data Index: 7725266 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7383. Min Range: -5.7383
Max Act: 5.5195. Min Act: -0.1700
Data Index: 2764751 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7383. Min Range: -5.7383
Max Act: 5.5508. Min Act: -0.1700
Data Index: 5057129 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7383. Min Range: -5.7383
Max Act: 5.5195. Min Act: -0.1700
Data Index: 4496738 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7383. Min Range: -5.7383
Max Act: 5.5508. Min Act: -0.1700
Data Index: 853845 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7383. Min Range: -5.7383
Max Act: 5.5195. Min Act: -0.1700
Data Index: 1701976 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7383. Min Range: -5.7383
Max Act: 5.5195. Min Act: -0.1700
Data Index: 8645875 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7383. Min Range: -5.7383
Max Act: 5.5508. Min Act: -0.1700
Data Index: 8147953 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7383. Min Range: -5.7383
Max Act: 5.4883. Min Act: -0.1700
Data Index: 493442 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7383. Min Range: -5.7383
Max Act: 5.4570. Min Act: -0.1700
Data Index: 6651244 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7383. Min Range: -5.7383
Max Act: 5.4883. Min Act: -0.1700
Data Index: 2258999 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19