Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5332 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5096. Min Range: -7.5096
Max Act: 7.5096. Min Act: -0.1700
Data Index: 6865827 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5096. Min Range: -7.5096
Max Act: 7.1659. Min Act: -0.1700
Data Index: 535944 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5096. Min Range: -7.5096
Max Act: 7.1034. Min Act: -0.1700
Data Index: 5970838 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5096. Min Range: -7.5096
Max Act: 7.1034. Min Act: -0.1700
Data Index: 2577210 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5096. Min Range: -7.5096
Max Act: 6.9471. Min Act: -0.1700
Data Index: 7448304 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5096. Min Range: -7.5096
Max Act: 6.8846. Min Act: -0.1700
Data Index: 4119410 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5096. Min Range: -7.5096
Max Act: 6.8534. Min Act: -0.1700
Data Index: 5028005 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5096. Min Range: -7.5096
Max Act: 6.8221. Min Act: -0.1700
Data Index: 1342306 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5096. Min Range: -7.5096
Max Act: 6.8221. Min Act: -0.1700
Data Index: 2843093 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5096. Min Range: -7.5096
Max Act: 6.7596. Min Act: -0.1700
Data Index: 451482 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5096. Min Range: -7.5096
Max Act: 6.7284. Min Act: -0.1700
Data Index: 2103173 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5096. Min Range: -7.5096
Max Act: 6.7284. Min Act: -0.1700
Data Index: 5266869 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5096. Min Range: -7.5096
Max Act: 6.6971. Min Act: -0.1700
Data Index: 4348269 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5096. Min Range: -7.5096
Max Act: 6.7284. Min Act: -0.1700
Data Index: 1989051 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5096. Min Range: -7.5096
Max Act: 6.6971. Min Act: -0.1700
Data Index: 7205925 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5096. Min Range: -7.5096
Max Act: 6.6346. Min Act: -0.1700
Data Index: 4370385 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5096. Min Range: -7.5096
Max Act: 6.6346. Min Act: -0.1700
Data Index: 4089947 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5096. Min Range: -7.5096
Max Act: 6.6659. Min Act: -0.1700
Data Index: 1405129 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5096. Min Range: -7.5096
Max Act: 6.6346. Min Act: -0.1700
Data Index: 4408298 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5096. Min Range: -7.5096
Max Act: 6.6346. Min Act: -0.1700
Data Index: 1468401 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19