Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 287 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.9567. Min Act: -0.1700
Data Index: 5443457 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.8942. Min Act: -0.1700
Data Index: 614576 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.9255. Min Act: -0.1700
Data Index: 7109939 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.8317. Min Act: -0.1700
Data Index: 6079866 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.7380. Min Act: -0.1700
Data Index: 6848989 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.7067. Min Act: -0.1700
Data Index: 4880193 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.6442. Min Act: -0.1700
Data Index: 8481920 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.6442. Min Act: -0.1700
Data Index: 5895594 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.5817. Min Act: -0.1700
Data Index: 6175701 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.5817. Min Act: -0.1700
Data Index: 7289049 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.5505. Min Act: -0.1700
Data Index: 404704 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.5192. Min Act: -0.1700
Data Index: 7861242 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.5505. Min Act: -0.1700
Data Index: 4839599 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.4567. Min Act: -0.1700
Data Index: 7473916 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.5505. Min Act: -0.1700
Data Index: 2485799 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.5192. Min Act: -0.1700
Data Index: 3646418 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.5505. Min Act: -0.1700
Data Index: 2639953 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.5192. Min Act: -0.1700
Data Index: 4177889 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.4880. Min Act: -0.1700
Data Index: 5781374 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.4880. Min Act: -0.1700
Data Index: 7453559 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19