Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3639 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0442. Min Range: -6.0442
Max Act: 6.0442. Min Act: -0.1700
Data Index: 3231884 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0442. Min Range: -6.0442
Max Act: 5.3567. Min Act: -0.1700
Data Index: 5636215 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0442. Min Range: -6.0442
Max Act: 5.3567. Min Act: -0.1700
Data Index: 7033288 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0442. Min Range: -6.0442
Max Act: 5.3255. Min Act: -0.1700
Data Index: 2371463 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0442. Min Range: -6.0442
Max Act: 5.3255. Min Act: -0.1700
Data Index: 7129677 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0442. Min Range: -6.0442
Max Act: 5.3255. Min Act: -0.1700
Data Index: 4844776 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0442. Min Range: -6.0442
Max Act: 5.2317. Min Act: -0.1700
Data Index: 830777 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0442. Min Range: -6.0442
Max Act: 5.2630. Min Act: -0.1700
Data Index: 8096118 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0442. Min Range: -6.0442
Max Act: 5.2630. Min Act: -0.1700
Data Index: 8041282 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0442. Min Range: -6.0442
Max Act: 5.2630. Min Act: -0.1700
Data Index: 1848785 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0442. Min Range: -6.0442
Max Act: 5.2630. Min Act: -0.1700
Data Index: 996312 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0442. Min Range: -6.0442
Max Act: 5.2005. Min Act: -0.1700
Data Index: 6746020 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0442. Min Range: -6.0442
Max Act: 5.1692. Min Act: -0.1700
Data Index: 7315928 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0442. Min Range: -6.0442
Max Act: 5.1692. Min Act: -0.1700
Data Index: 5648346 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0442. Min Range: -6.0442
Max Act: 5.1380. Min Act: -0.1700
Data Index: 7794782 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0442. Min Range: -6.0442
Max Act: 5.1380. Min Act: -0.1700
Data Index: 4218808 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0442. Min Range: -6.0442
Max Act: 5.1380. Min Act: -0.1700
Data Index: 5344621 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0442. Min Range: -6.0442
Max Act: 5.1067. Min Act: -0.1700
Data Index: 6260 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0442. Min Range: -6.0442
Max Act: 5.1380. Min Act: -0.1700
Data Index: 2864327 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0442. Min Range: -6.0442
Max Act: 5.1067. Min Act: -0.1700
Data Index: 192721 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19