Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1817 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6567. Min Range: -5.6567
Max Act: 5.6567. Min Act: -0.1700
Data Index: 7804543 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6567. Min Range: -5.6567
Max Act: 5.6255. Min Act: -0.1700
Data Index: 4674660 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6567. Min Range: -5.6567
Max Act: 5.5005. Min Act: -0.1700
Data Index: 4902781 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6567. Min Range: -5.6567
Max Act: 5.4380. Min Act: -0.1700
Data Index: 8180584 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6567. Min Range: -5.6567
Max Act: 5.3442. Min Act: -0.1700
Data Index: 5997312 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6567. Min Range: -5.6567
Max Act: 5.2505. Min Act: -0.1700
Data Index: 1840486 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6567. Min Range: -5.6567
Max Act: 5.2192. Min Act: -0.1700
Data Index: 8096482 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6567. Min Range: -5.6567
Max Act: 5.2192. Min Act: -0.1700
Data Index: 5981690 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6567. Min Range: -5.6567
Max Act: 5.1880. Min Act: -0.1700
Data Index: 5314093 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6567. Min Range: -5.6567
Max Act: 5.2192. Min Act: -0.1700
Data Index: 4372315 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6567. Min Range: -5.6567
Max Act: 5.1880. Min Act: -0.1700
Data Index: 201233 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6567. Min Range: -5.6567
Max Act: 5.1567. Min Act: -0.1700
Data Index: 7438747 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6567. Min Range: -5.6567
Max Act: 5.1255. Min Act: -0.1700
Data Index: 1638014 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6567. Min Range: -5.6567
Max Act: 5.1567. Min Act: -0.1700
Data Index: 8772403 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6567. Min Range: -5.6567
Max Act: 5.1567. Min Act: -0.1700
Data Index: 372180 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6567. Min Range: -5.6567
Max Act: 5.1255. Min Act: -0.1700
Data Index: 6334658 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6567. Min Range: -5.6567
Max Act: 5.0942. Min Act: -0.1700
Data Index: 4707585 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6567. Min Range: -5.6567
Max Act: 5.1255. Min Act: -0.1700
Data Index: 6589605 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6567. Min Range: -5.6567
Max Act: 5.0942. Min Act: -0.1700
Data Index: 4226679 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6567. Min Range: -5.6567
Max Act: 5.0630. Min Act: -0.1700
Data Index: 3185822 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19