Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5745 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6346. Min Range: -10.6346
Max Act: 10.6346. Min Act: -0.1700
Data Index: 710982 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6346. Min Range: -10.6346
Max Act: 10.0721. Min Act: -0.1700
Data Index: 5325303 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6346. Min Range: -10.6346
Max Act: 9.8846. Min Act: -0.1700
Data Index: 1115039 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6346. Min Range: -10.6346
Max Act: 9.8846. Min Act: -0.1700
Data Index: 3455253 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6346. Min Range: -10.6346
Max Act: 9.8221. Min Act: -0.1700
Data Index: 1769638 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6346. Min Range: -10.6346
Max Act: 9.8221. Min Act: -0.1700
Data Index: 1502458 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6346. Min Range: -10.6346
Max Act: 9.7596. Min Act: -0.1700
Data Index: 7640269 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6346. Min Range: -10.6346
Max Act: 9.6971. Min Act: -0.1700
Data Index: 2345684 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6346. Min Range: -10.6346
Max Act: 9.6971. Min Act: -0.1700
Data Index: 6111448 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6346. Min Range: -10.6346
Max Act: 9.7596. Min Act: -0.1700
Data Index: 7474310 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6346. Min Range: -10.6346
Max Act: 9.6971. Min Act: -0.1700
Data Index: 1960769 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6346. Min Range: -10.6346
Max Act: 9.6346. Min Act: -0.1700
Data Index: 6235895 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6346. Min Range: -10.6346
Max Act: 9.6346. Min Act: -0.1700
Data Index: 4046221 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6346. Min Range: -10.6346
Max Act: 9.4471. Min Act: -0.1700
Data Index: 6121867 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6346. Min Range: -10.6346
Max Act: 9.4471. Min Act: -0.1700
Data Index: 5581613 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6346. Min Range: -10.6346
Max Act: 9.3846. Min Act: -0.1700
Data Index: 6956913 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6346. Min Range: -10.6346
Max Act: 9.3846. Min Act: -0.1700
Data Index: 5389270 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6346. Min Range: -10.6346
Max Act: 9.3221. Min Act: -0.1700
Data Index: 808823 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6346. Min Range: -10.6346
Max Act: 9.3221. Min Act: -0.1700
Data Index: 754557 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6346. Min Range: -10.6346
Max Act: 9.3221. Min Act: -0.1700
Data Index: 3444629 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19