Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3658 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.7692. Min Act: -0.1700
Data Index: 347104 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.6755. Min Act: -0.1700
Data Index: 2228855 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.6442. Min Act: -0.1700
Data Index: 6448107 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.5817. Min Act: -0.1700
Data Index: 1283193 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.5505. Min Act: -0.1700
Data Index: 3510810 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.5505. Min Act: -0.1700
Data Index: 5659158 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.5192. Min Act: -0.1700
Data Index: 3678227 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.4880. Min Act: -0.1700
Data Index: 7213369 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.4880. Min Act: -0.1700
Data Index: 6873028 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.4567. Min Act: -0.1700
Data Index: 1087186 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.5192. Min Act: -0.1700
Data Index: 6946625 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.4567. Min Act: -0.1700
Data Index: 4716742 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.4567. Min Act: -0.1700
Data Index: 375644 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.4255. Min Act: -0.1700
Data Index: 2924859 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.3942. Min Act: -0.1700
Data Index: 3390050 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.4255. Min Act: -0.1700
Data Index: 1147122 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.3942. Min Act: -0.1700
Data Index: 2755190 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.3630. Min Act: -0.1700
Data Index: 3705268 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.3317. Min Act: -0.1700
Data Index: 758740 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7692. Min Range: -5.7692
Max Act: 5.3630. Min Act: -0.1700
Data Index: 3667188 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19