Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2328 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5302. Min Range: -3.5302
Max Act: 3.5302. Min Act: -0.1700
Data Index: 4736589 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5302. Min Range: -3.5302
Max Act: 3.4989. Min Act: -0.1700
Data Index: 7905988 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5302. Min Range: -3.5302
Max Act: 3.4048. Min Act: -0.1700
Data Index: 8262816 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5302. Min Range: -3.5302
Max Act: 3.4205. Min Act: -0.1700
Data Index: 1178653 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5302. Min Range: -3.5302
Max Act: 3.3892. Min Act: -0.1700
Data Index: 4746637 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5302. Min Range: -3.5302
Max Act: 3.3735. Min Act: -0.1700
Data Index: 1628426 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5302. Min Range: -3.5302
Max Act: 3.3735. Min Act: -0.1700
Data Index: 6576724 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5302. Min Range: -3.5302
Max Act: 3.3578. Min Act: -0.1700
Data Index: 4718752 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5302. Min Range: -3.5302
Max Act: 3.3578. Min Act: -0.1700
Data Index: 5010821 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5302. Min Range: -3.5302
Max Act: 3.3578. Min Act: -0.1700
Data Index: 85772 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5302. Min Range: -3.5302
Max Act: 3.3421. Min Act: -0.1700
Data Index: 5372566 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5302. Min Range: -3.5302
Max Act: 3.3264. Min Act: -0.1700
Data Index: 3268545 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5302. Min Range: -3.5302
Max Act: 3.3264. Min Act: -0.1700
Data Index: 3000052 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5302. Min Range: -3.5302
Max Act: 3.3107. Min Act: -0.1700
Data Index: 8546190 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5302. Min Range: -3.5302
Max Act: 3.3107. Min Act: -0.1700
Data Index: 6034919 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5302. Min Range: -3.5302
Max Act: 3.2793. Min Act: -0.1700
Data Index: 5738442 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5302. Min Range: -3.5302
Max Act: 3.2636. Min Act: -0.1700
Data Index: 1628425 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5302. Min Range: -3.5302
Max Act: 3.2793. Min Act: -0.1700
Data Index: 2378769 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5302. Min Range: -3.5302
Max Act: 3.2636. Min Act: -0.1700
Data Index: 8600514 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5302. Min Range: -3.5302
Max Act: 3.2636. Min Act: -0.1700
Data Index: 6056675 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19