Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3548 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6744. Min Range: -6.6744
Max Act: 6.6744. Min Act: -0.1700
Data Index: 8565038 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6744. Min Range: -6.6744
Max Act: 6.4869. Min Act: -0.1700
Data Index: 3551166 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6744. Min Range: -6.6744
Max Act: 6.3932. Min Act: -0.1700
Data Index: 385955 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6744. Min Range: -6.6744
Max Act: 6.3619. Min Act: -0.1700
Data Index: 2501262 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6744. Min Range: -6.6744
Max Act: 6.2682. Min Act: -0.1700
Data Index: 2757559 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6744. Min Range: -6.6744
Max Act: 6.2682. Min Act: -0.1700
Data Index: 7382317 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6744. Min Range: -6.6744
Max Act: 6.2369. Min Act: -0.1697
Data Index: 2849807 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6744. Min Range: -6.6744
Max Act: 6.2057. Min Act: -0.1700
Data Index: 6229827 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6744. Min Range: -6.6744
Max Act: 6.1432. Min Act: -0.1700
Data Index: 1332443 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6744. Min Range: -6.6744
Max Act: 6.1432. Min Act: -0.1700
Data Index: 7672080 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6744. Min Range: -6.6744
Max Act: 6.1744. Min Act: -0.1699
Data Index: 3975379 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6744. Min Range: -6.6744
Max Act: 6.1432. Min Act: -0.1700
Data Index: 5800886 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6744. Min Range: -6.6744
Max Act: 6.1744. Min Act: -0.1700
Data Index: 4129112 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6744. Min Range: -6.6744
Max Act: 6.1432. Min Act: -0.1700
Data Index: 4755456 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6744. Min Range: -6.6744
Max Act: 6.1119. Min Act: -0.1700
Data Index: 1267563 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6744. Min Range: -6.6744
Max Act: 6.1432. Min Act: -0.1700
Data Index: 8093537 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6744. Min Range: -6.6744
Max Act: 6.1119. Min Act: -0.1699
Data Index: 7584259 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6744. Min Range: -6.6744
Max Act: 6.1432. Min Act: -0.1700
Data Index: 6357844 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6744. Min Range: -6.6744
Max Act: 6.1119. Min Act: -0.1700
Data Index: 4022165 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6744. Min Range: -6.6744
Max Act: 6.0807. Min Act: -0.1697
Data Index: 8259250 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19