Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1892 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7929. Min Range: -4.7929
Max Act: 4.7929. Min Act: -0.1700
Data Index: 1345364 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7929. Min Range: -4.7929
Max Act: 4.5742. Min Act: -0.1700
Data Index: 134950 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7929. Min Range: -4.7929
Max Act: 4.5429. Min Act: -0.1700
Data Index: 1345365 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7929. Min Range: -4.7929
Max Act: 4.5429. Min Act: -0.1700
Data Index: 4161840 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7929. Min Range: -4.7929
Max Act: 4.5117. Min Act: -0.1700
Data Index: 5915529 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7929. Min Range: -4.7929
Max Act: 4.5429. Min Act: -0.1700
Data Index: 6814434 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7929. Min Range: -4.7929
Max Act: 4.4804. Min Act: -0.1700
Data Index: 8381584 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7929. Min Range: -4.7929
Max Act: 4.4804. Min Act: -0.1700
Data Index: 2995667 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7929. Min Range: -4.7929
Max Act: 4.4179. Min Act: -0.1700
Data Index: 4495821 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7929. Min Range: -4.7929
Max Act: 4.4492. Min Act: -0.1700
Data Index: 2272205 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7929. Min Range: -4.7929
Max Act: 4.4492. Min Act: -0.1700
Data Index: 7640157 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7929. Min Range: -4.7929
Max Act: 4.4492. Min Act: -0.1700
Data Index: 6489905 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7929. Min Range: -4.7929
Max Act: 4.4492. Min Act: -0.1700
Data Index: 920506 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7929. Min Range: -4.7929
Max Act: 4.4492. Min Act: -0.1700
Data Index: 2479288 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7929. Min Range: -4.7929
Max Act: 4.4179. Min Act: -0.1700
Data Index: 5956327 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7929. Min Range: -4.7929
Max Act: 4.4179. Min Act: -0.1700
Data Index: 717693 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7929. Min Range: -4.7929
Max Act: 4.4179. Min Act: -0.1700
Data Index: 4933400 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7929. Min Range: -4.7929
Max Act: 4.4179. Min Act: -0.1700
Data Index: 2936150 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7929. Min Range: -4.7929
Max Act: 4.4179. Min Act: -0.1700
Data Index: 5981309 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7929. Min Range: -4.7929
Max Act: 4.4179. Min Act: -0.1700
Data Index: 1556747 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19