Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4331 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9016. Min Range: -4.9016
Max Act: 4.9016. Min Act: -0.1700
Data Index: 5626320 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9016. Min Range: -4.9016
Max Act: 4.8703. Min Act: -0.1700
Data Index: 4618500 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9016. Min Range: -4.9016
Max Act: 4.8391. Min Act: -0.1700
Data Index: 4358973 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9016. Min Range: -4.9016
Max Act: 4.7766. Min Act: -0.1700
Data Index: 6841043 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9016. Min Range: -4.9016
Max Act: 4.7766. Min Act: -0.1700
Data Index: 2416661 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9016. Min Range: -4.9016
Max Act: 4.6828. Min Act: -0.1700
Data Index: 8132279 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9016. Min Range: -4.9016
Max Act: 4.6203. Min Act: -0.1700
Data Index: 380414 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9016. Min Range: -4.9016
Max Act: 4.5891. Min Act: -0.1700
Data Index: 1514689 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9016. Min Range: -4.9016
Max Act: 4.6203. Min Act: -0.1700
Data Index: 2813140 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9016. Min Range: -4.9016
Max Act: 4.5891. Min Act: -0.1700
Data Index: 4415743 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9016. Min Range: -4.9016
Max Act: 4.5578. Min Act: -0.1700
Data Index: 2332811 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9016. Min Range: -4.9016
Max Act: 4.5266. Min Act: -0.1700
Data Index: 1782422 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9016. Min Range: -4.9016
Max Act: 4.4953. Min Act: -0.1700
Data Index: 3712236 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9016. Min Range: -4.9016
Max Act: 4.4953. Min Act: -0.1700
Data Index: 2049957 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9016. Min Range: -4.9016
Max Act: 4.4953. Min Act: -0.1700
Data Index: 6636647 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9016. Min Range: -4.9016
Max Act: 4.4953. Min Act: -0.1700
Data Index: 8738261 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9016. Min Range: -4.9016
Max Act: 4.4953. Min Act: -0.1700
Data Index: 2178464 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9016. Min Range: -4.9016
Max Act: 4.4328. Min Act: -0.1700
Data Index: 6856343 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9016. Min Range: -4.9016
Max Act: 4.4328. Min Act: -0.1700
Data Index: 7739528 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9016. Min Range: -4.9016
Max Act: 4.4953. Min Act: -0.1700
Data Index: 3645540 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19