Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3499 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2951. Min Range: -3.2951
Max Act: 3.2794. Min Act: -0.1700
Data Index: 2537798 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2951. Min Range: -3.2951
Max Act: 3.2951. Min Act: -0.1700
Data Index: 6841877 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2951. Min Range: -3.2951
Max Act: 3.2637. Min Act: -0.1700
Data Index: 8623728 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2951. Min Range: -3.2951
Max Act: 3.2009. Min Act: -0.1700
Data Index: 4415070 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2951. Min Range: -3.2951
Max Act: 3.2009. Min Act: -0.1700
Data Index: 1284616 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2951. Min Range: -3.2951
Max Act: 3.1537. Min Act: -0.1700
Data Index: 6318835 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2951. Min Range: -3.2951
Max Act: 3.1537. Min Act: -0.1700
Data Index: 5804433 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2951. Min Range: -3.2951
Max Act: 3.1537. Min Act: -0.1700
Data Index: 429585 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2951. Min Range: -3.2951
Max Act: 3.1064. Min Act: -0.1700
Data Index: 1756293 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2951. Min Range: -3.2951
Max Act: 3.1379. Min Act: -0.1700
Data Index: 7082382 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2951. Min Range: -3.2951
Max Act: 3.1379. Min Act: -0.1700
Data Index: 7278557 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2951. Min Range: -3.2951
Max Act: 3.1537. Min Act: -0.1700
Data Index: 5297669 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2951. Min Range: -3.2951
Max Act: 3.1222. Min Act: -0.1700
Data Index: 164448 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2951. Min Range: -3.2951
Max Act: 3.1222. Min Act: -0.1700
Data Index: 68607 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2951. Min Range: -3.2951
Max Act: 3.1222. Min Act: -0.1700
Data Index: 2025006 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2951. Min Range: -3.2951
Max Act: 3.1222. Min Act: -0.1700
Data Index: 1865361 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2951. Min Range: -3.2951
Max Act: 3.1064. Min Act: -0.1700
Data Index: 571292 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2951. Min Range: -3.2951
Max Act: 3.1379. Min Act: -0.1700
Data Index: 2607962 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2951. Min Range: -3.2951
Max Act: 3.1064. Min Act: -0.1700
Data Index: 2505587 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2951. Min Range: -3.2951
Max Act: 3.1064. Min Act: -0.1700
Data Index: 4283045 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19