Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4744 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0024. Min Range: -8.0024
Max Act: 8.0024. Min Act: -0.1700
Data Index: 4441758 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0024. Min Range: -8.0024
Max Act: 7.4086. Min Act: -0.1700
Data Index: 8628882 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0024. Min Range: -8.0024
Max Act: 7.4086. Min Act: -0.1700
Data Index: 6613304 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0024. Min Range: -8.0024
Max Act: 7.3774. Min Act: -0.1700
Data Index: 2096673 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0024. Min Range: -8.0024
Max Act: 7.1586. Min Act: -0.1700
Data Index: 4075929 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0024. Min Range: -8.0024
Max Act: 7.1899. Min Act: -0.1700
Data Index: 6812334 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0024. Min Range: -8.0024
Max Act: 7.0961. Min Act: -0.1700
Data Index: 2838823 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0024. Min Range: -8.0024
Max Act: 7.0961. Min Act: -0.1700
Data Index: 8230545 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0024. Min Range: -8.0024
Max Act: 7.0649. Min Act: -0.1700
Data Index: 8738187 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0024. Min Range: -8.0024
Max Act: 7.0649. Min Act: -0.1700
Data Index: 213209 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0024. Min Range: -8.0024
Max Act: 7.0961. Min Act: -0.1700
Data Index: 131620 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0024. Min Range: -8.0024
Max Act: 7.1274. Min Act: -0.1700
Data Index: 6799244 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0024. Min Range: -8.0024
Max Act: 7.0336. Min Act: -0.1700
Data Index: 5242935 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0024. Min Range: -8.0024
Max Act: 7.0649. Min Act: -0.1700
Data Index: 8141022 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0024. Min Range: -8.0024
Max Act: 7.0336. Min Act: -0.1700
Data Index: 18838 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0024. Min Range: -8.0024
Max Act: 7.0024. Min Act: -0.1700
Data Index: 5765010 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0024. Min Range: -8.0024
Max Act: 7.0024. Min Act: -0.1700
Data Index: 1383171 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0024. Min Range: -8.0024
Max Act: 7.0649. Min Act: -0.1700
Data Index: 4119831 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0024. Min Range: -8.0024
Max Act: 7.0024. Min Act: -0.1700
Data Index: 8552030 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0024. Min Range: -8.0024
Max Act: 7.0024. Min Act: -0.1700
Data Index: 3490002 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19