Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 26 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1528. Min Range: -4.1528
Max Act: 4.1528. Min Act: -0.1700
Data Index: 3820720 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1528. Min Range: -4.1528
Max Act: 4.0903. Min Act: -0.1700
Data Index: 5387861 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1528. Min Range: -4.1528
Max Act: 4.0278. Min Act: -0.1700
Data Index: 224414 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1528. Min Range: -4.1528
Max Act: 3.9965. Min Act: -0.1700
Data Index: 3360382 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1528. Min Range: -4.1528
Max Act: 3.9340. Min Act: -0.1700
Data Index: 1758994 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1528. Min Range: -4.1528
Max Act: 3.9340. Min Act: -0.1700
Data Index: 4729048 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1528. Min Range: -4.1528
Max Act: 3.9340. Min Act: -0.1700
Data Index: 8697879 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1528. Min Range: -4.1528
Max Act: 3.9653. Min Act: -0.1700
Data Index: 4469307 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1528. Min Range: -4.1528
Max Act: 3.9340. Min Act: -0.1700
Data Index: 2754509 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1528. Min Range: -4.1528
Max Act: 3.9340. Min Act: -0.1700
Data Index: 574247 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1528. Min Range: -4.1528
Max Act: 3.8715. Min Act: -0.1700
Data Index: 6433189 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1528. Min Range: -4.1528
Max Act: 3.9027. Min Act: -0.1700
Data Index: 3315051 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1528. Min Range: -4.1528
Max Act: 3.9027. Min Act: -0.1700
Data Index: 7113255 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1528. Min Range: -4.1528
Max Act: 3.9027. Min Act: -0.1700
Data Index: 3160221 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1528. Min Range: -4.1528
Max Act: 3.8715. Min Act: -0.1700
Data Index: 7800011 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1528. Min Range: -4.1528
Max Act: 3.8715. Min Act: -0.1700
Data Index: 8814462 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1528. Min Range: -4.1528
Max Act: 3.8715. Min Act: -0.1700
Data Index: 3797827 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1528. Min Range: -4.1528
Max Act: 3.8402. Min Act: -0.1700
Data Index: 6794948 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1528. Min Range: -4.1528
Max Act: 3.8715. Min Act: -0.1700
Data Index: 6983262 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1528. Min Range: -4.1528
Max Act: 3.8715. Min Act: -0.1700
Data Index: 4786877 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19