Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 292 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8254. Min Range: -8.8254
Max Act: 8.8254. Min Act: -0.1700
Data Index: 3744494 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8254. Min Range: -8.8254
Max Act: 8.5754. Min Act: -0.1700
Data Index: 5859150 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8254. Min Range: -8.8254
Max Act: 8.4504. Min Act: -0.1700
Data Index: 19982 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8254. Min Range: -8.8254
Max Act: 8.5129. Min Act: -0.1700
Data Index: 1913250 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8254. Min Range: -8.8254
Max Act: 8.4192. Min Act: -0.1700
Data Index: 217883 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8254. Min Range: -8.8254
Max Act: 8.3567. Min Act: -0.1700
Data Index: 3559908 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8254. Min Range: -8.8254
Max Act: 8.3567. Min Act: -0.1700
Data Index: 217882 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8254. Min Range: -8.8254
Max Act: 8.2629. Min Act: -0.1700
Data Index: 1931522 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8254. Min Range: -8.8254
Max Act: 8.2629. Min Act: -0.1700
Data Index: 5687530 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8254. Min Range: -8.8254
Max Act: 8.2942. Min Act: -0.1700
Data Index: 6945709 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8254. Min Range: -8.8254
Max Act: 8.2317. Min Act: -0.1700
Data Index: 6512740 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8254. Min Range: -8.8254
Max Act: 8.1692. Min Act: -0.1700
Data Index: 870153 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8254. Min Range: -8.8254
Max Act: 8.1379. Min Act: -0.1700
Data Index: 19958 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8254. Min Range: -8.8254
Max Act: 8.1067. Min Act: -0.1700
Data Index: 1594527 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8254. Min Range: -8.8254
Max Act: 8.0129. Min Act: -0.1700
Data Index: 19972 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8254. Min Range: -8.8254
Max Act: 8.0129. Min Act: -0.1700
Data Index: 855120 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8254. Min Range: -8.8254
Max Act: 7.9504. Min Act: -0.1700
Data Index: 6047971 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8254. Min Range: -8.8254
Max Act: 7.9817. Min Act: -0.1700
Data Index: 19967 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8254. Min Range: -8.8254
Max Act: 7.9504. Min Act: -0.1700
Data Index: 19973 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8254. Min Range: -8.8254
Max Act: 7.9192. Min Act: -0.1700
Data Index: 6069445 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19