Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 254 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5809. Min Range: -1.5809
Max Act: 1.5809. Min Act: -0.1699
Data Index: 6468120 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5809. Min Range: -1.5809
Max Act: 1.5459. Min Act: -0.1700
Data Index: 795367 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5809. Min Range: -1.5809
Max Act: 1.5459. Min Act: -0.1700
Data Index: 4620379 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5809. Min Range: -1.5809
Max Act: 1.5371. Min Act: -0.1700
Data Index: 8329238 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5809. Min Range: -1.5809
Max Act: 1.5108. Min Act: -0.1689
Data Index: 7269196 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5809. Min Range: -1.5809
Max Act: 1.5108. Min Act: -0.1700
Data Index: 5081695 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5809. Min Range: -1.5809
Max Act: 1.5020. Min Act: -0.1700
Data Index: 8009953 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5809. Min Range: -1.5809
Max Act: 1.5020. Min Act: -0.1700
Data Index: 3267999 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5809. Min Range: -1.5809
Max Act: 1.4932. Min Act: -0.1700
Data Index: 6590329 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5809. Min Range: -1.5809
Max Act: 1.4757. Min Act: -0.1700
Data Index: 1084062 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5809. Min Range: -1.5809
Max Act: 1.4757. Min Act: -0.1700
Data Index: 1445334 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5809. Min Range: -1.5809
Max Act: 1.4757. Min Act: -0.1700
Data Index: 709432 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5809. Min Range: -1.5809
Max Act: 1.4757. Min Act: -0.1687
Data Index: 6098036 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5809. Min Range: -1.5809
Max Act: 1.4581. Min Act: -0.1694
Data Index: 1798293 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5809. Min Range: -1.5809
Max Act: 1.4669. Min Act: -0.1696
Data Index: 3743921 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5809. Min Range: -1.5809
Max Act: 1.4493. Min Act: -0.1700
Data Index: 2470232 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5809. Min Range: -1.5809
Max Act: 1.4581. Min Act: -0.1700
Data Index: 5540338 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5809. Min Range: -1.5809
Max Act: 1.4493. Min Act: -0.1700
Data Index: 8617684 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5809. Min Range: -1.5809
Max Act: 1.4581. Min Act: -0.1698
Data Index: 1351637 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5809. Min Range: -1.5809
Max Act: 1.4581. Min Act: -0.1698
Data Index: 170983 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19