Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 947 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.7826. Min Range: -0.7826
Max Act: 0.7826. Min Act: -0.1690
Data Index: 3032836 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7826. Min Range: -0.7826
Max Act: 0.7659. Min Act: -0.1699
Data Index: 6238919 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7826. Min Range: -0.7826
Max Act: 0.7659. Min Act: -0.1700
Data Index: 5916474 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7826. Min Range: -0.7826
Max Act: 0.7493. Min Act: -0.1695
Data Index: 8129231 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7826. Min Range: -0.7826
Max Act: 0.7493. Min Act: -0.1700
Data Index: 3205596 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7826. Min Range: -0.7826
Max Act: 0.7493. Min Act: -0.1700
Data Index: 6436434 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7826. Min Range: -0.7826
Max Act: 0.7411. Min Act: -0.1700
Data Index: 5953912 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7826. Min Range: -0.7826
Max Act: 0.7246. Min Act: -0.1686
Data Index: 7557748 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7826. Min Range: -0.7826
Max Act: 0.7246. Min Act: -0.1699
Data Index: 3983007 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7826. Min Range: -0.7826
Max Act: 0.7164. Min Act: -0.1693
Data Index: 3032839 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7826. Min Range: -0.7826
Max Act: 0.7082. Min Act: -0.1682
Data Index: 6277371 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7826. Min Range: -0.7826
Max Act: 0.7000. Min Act: -0.1680
Data Index: 6165745 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7826. Min Range: -0.7826
Max Act: 0.6919. Min Act: -0.1700
Data Index: 907779 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7826. Min Range: -0.7826
Max Act: 0.6919. Min Act: -0.1683
Data Index: 8009352 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7826. Min Range: -0.7826
Max Act: 0.7000. Min Act: -0.1680
Data Index: 4807032 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7826. Min Range: -0.7826
Max Act: 0.6837. Min Act: -0.1692
Data Index: 4170973 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7826. Min Range: -0.7826
Max Act: 0.6919. Min Act: -0.1676
Data Index: 6417202 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7826. Min Range: -0.7826
Max Act: 0.6919. Min Act: -0.1700
Data Index: 7137935 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7826. Min Range: -0.7826
Max Act: 0.6919. Min Act: -0.1655
Data Index: 3907798 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7826. Min Range: -0.7826
Max Act: 0.6919. Min Act: -0.1695
Data Index: 6262225 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19