Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5888 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7486. Min Range: -5.7486
Max Act: 5.7486. Min Act: -0.1700
Data Index: 5394027 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7486. Min Range: -5.7486
Max Act: 5.6548. Min Act: -0.1700
Data Index: 1332694 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7486. Min Range: -5.7486
Max Act: 5.6548. Min Act: -0.1700
Data Index: 860940 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7486. Min Range: -5.7486
Max Act: 5.6236. Min Act: -0.1700
Data Index: 4775350 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7486. Min Range: -5.7486
Max Act: 5.5923. Min Act: -0.1700
Data Index: 3709206 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7486. Min Range: -5.7486
Max Act: 5.5923. Min Act: -0.1700
Data Index: 7315611 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7486. Min Range: -5.7486
Max Act: 5.5611. Min Act: -0.1700
Data Index: 1994772 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7486. Min Range: -5.7486
Max Act: 5.5298. Min Act: -0.1700
Data Index: 3490719 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7486. Min Range: -5.7486
Max Act: 5.5298. Min Act: -0.1700
Data Index: 5374903 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7486. Min Range: -5.7486
Max Act: 5.4361. Min Act: -0.1700
Data Index: 7224134 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7486. Min Range: -5.7486
Max Act: 5.4361. Min Act: -0.1700
Data Index: 8630519 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7486. Min Range: -5.7486
Max Act: 5.4361. Min Act: -0.1700
Data Index: 3674539 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7486. Min Range: -5.7486
Max Act: 5.4048. Min Act: -0.1700
Data Index: 2196236 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7486. Min Range: -5.7486
Max Act: 5.3736. Min Act: -0.1700
Data Index: 4695047 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7486. Min Range: -5.7486
Max Act: 5.3423. Min Act: -0.1700
Data Index: 5206258 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7486. Min Range: -5.7486
Max Act: 5.3423. Min Act: -0.1700
Data Index: 1268557 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7486. Min Range: -5.7486
Max Act: 5.3111. Min Act: -0.1700
Data Index: 7304542 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7486. Min Range: -5.7486
Max Act: 5.3111. Min Act: -0.1700
Data Index: 3630560 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7486. Min Range: -5.7486
Max Act: 5.2798. Min Act: -0.1700
Data Index: 689788 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7486. Min Range: -5.7486
Max Act: 5.2798. Min Act: -0.1700
Data Index: 3650339 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19