Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3130 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2272. Min Range: -7.2272
Max Act: 7.2272. Min Act: -0.1700
Data Index: 3965032 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2272. Min Range: -7.2272
Max Act: 7.1959. Min Act: -0.1700
Data Index: 1458023 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2272. Min Range: -7.2272
Max Act: 7.1647. Min Act: -0.1700
Data Index: 2180040 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2272. Min Range: -7.2272
Max Act: 7.1022. Min Act: -0.1700
Data Index: 3497852 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2272. Min Range: -7.2272
Max Act: 7.1022. Min Act: -0.1700
Data Index: 4185415 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2272. Min Range: -7.2272
Max Act: 7.0709. Min Act: -0.1700
Data Index: 1079567 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2272. Min Range: -7.2272
Max Act: 7.0709. Min Act: -0.1700
Data Index: 4250245 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2272. Min Range: -7.2272
Max Act: 7.0397. Min Act: -0.1700
Data Index: 3468305 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2272. Min Range: -7.2272
Max Act: 7.0397. Min Act: -0.1700
Data Index: 5773383 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2272. Min Range: -7.2272
Max Act: 7.0397. Min Act: -0.1700
Data Index: 952657 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2272. Min Range: -7.2272
Max Act: 7.0397. Min Act: -0.1700
Data Index: 3500783 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2272. Min Range: -7.2272
Max Act: 7.0397. Min Act: -0.1700
Data Index: 5016848 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2272. Min Range: -7.2272
Max Act: 7.0397. Min Act: -0.1700
Data Index: 4643646 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2272. Min Range: -7.2272
Max Act: 7.0084. Min Act: -0.1700
Data Index: 4581303 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2272. Min Range: -7.2272
Max Act: 7.0084. Min Act: -0.1700
Data Index: 4668115 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2272. Min Range: -7.2272
Max Act: 6.9772. Min Act: -0.1700
Data Index: 7669451 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2272. Min Range: -7.2272
Max Act: 6.9147. Min Act: -0.1700
Data Index: 8202861 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2272. Min Range: -7.2272
Max Act: 6.8834. Min Act: -0.1700
Data Index: 8313594 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2272. Min Range: -7.2272
Max Act: 6.9147. Min Act: -0.1700
Data Index: 5624622 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2272. Min Range: -7.2272
Max Act: 6.8522. Min Act: -0.1700
Data Index: 792590 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19