Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2767 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4796. Min Range: -1.4796
Max Act: 1.4796. Min Act: -0.1700
Data Index: 8301574 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4796. Min Range: -1.4796
Max Act: 1.4708. Min Act: -0.1622
Data Index: 6474111 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4796. Min Range: -1.4796
Max Act: 1.4532. Min Act: -0.1196
Data Index: 277435 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4796. Min Range: -1.4796
Max Act: 1.4268. Min Act: -0.1592
Data Index: 4537788 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4796. Min Range: -1.4796
Max Act: 1.4180. Min Act: -0.1700
Data Index: 647467 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4796. Min Range: -1.4796
Max Act: 1.4092. Min Act: -0.1700
Data Index: 5457305 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4796. Min Range: -1.4796
Max Act: 1.4092. Min Act: -0.1690
Data Index: 7318039 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4796. Min Range: -1.4796
Max Act: 1.4092. Min Act: -0.1688
Data Index: 6998871 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4796. Min Range: -1.4796
Max Act: 1.4004. Min Act: -0.1086
Data Index: 8795989 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4796. Min Range: -1.4796
Max Act: 1.4004. Min Act: -0.1665
Data Index: 4152100 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4796. Min Range: -1.4796
Max Act: 1.3916. Min Act: -0.1167
Data Index: 8182791 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4796. Min Range: -1.4796
Max Act: 1.3652. Min Act: -0.1485
Data Index: 6787170 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4796. Min Range: -1.4796
Max Act: 1.3563. Min Act: -0.1692
Data Index: 4060022 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4796. Min Range: -1.4796
Max Act: 1.3563. Min Act: -0.1631
Data Index: 7621850 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4796. Min Range: -1.4796
Max Act: 1.3652. Min Act: -0.1699
Data Index: 7488986 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4796. Min Range: -1.4796
Max Act: 1.3563. Min Act: -0.1700
Data Index: 7830663 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4796. Min Range: -1.4796
Max Act: 1.3475. Min Act: -0.1630
Data Index: 121993 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4796. Min Range: -1.4796
Max Act: 1.3563. Min Act: -0.1685
Data Index: 5130418 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4796. Min Range: -1.4796
Max Act: 1.3563. Min Act: -0.1698
Data Index: 6607093 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4796. Min Range: -1.4796
Max Act: 1.3475. Min Act: -0.1669
Data Index: 2531659 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19