Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5003 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0725. Min Range: -4.0725
Max Act: 4.0725. Min Act: -0.1700
Data Index: 5924233 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0725. Min Range: -4.0725
Max Act: 4.0412. Min Act: -0.1700
Data Index: 7599770 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0725. Min Range: -4.0725
Max Act: 3.7754. Min Act: -0.1700
Data Index: 4841423 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0725. Min Range: -4.0725
Max Act: 3.7598. Min Act: -0.1700
Data Index: 8778564 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0725. Min Range: -4.0725
Max Act: 3.7129. Min Act: -0.1700
Data Index: 2663697 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0725. Min Range: -4.0725
Max Act: 3.6972. Min Act: -0.1700
Data Index: 680595 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0725. Min Range: -4.0725
Max Act: 3.6347. Min Act: -0.1700
Data Index: 1557439 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0725. Min Range: -4.0725
Max Act: 3.6190. Min Act: -0.1700
Data Index: 5678142 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0725. Min Range: -4.0725
Max Act: 3.6034. Min Act: -0.1700
Data Index: 6063695 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0725. Min Range: -4.0725
Max Act: 3.5564. Min Act: -0.1700
Data Index: 8354210 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0725. Min Range: -4.0725
Max Act: 3.5407. Min Act: -0.1700
Data Index: 7229728 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0725. Min Range: -4.0725
Max Act: 3.5251. Min Act: -0.1700
Data Index: 3690907 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0725. Min Range: -4.0725
Max Act: 3.5251. Min Act: -0.1700
Data Index: 831578 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0725. Min Range: -4.0725
Max Act: 3.4938. Min Act: -0.1700
Data Index: 2065355 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0725. Min Range: -4.0725
Max Act: 3.4781. Min Act: -0.1700
Data Index: 6462183 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0725. Min Range: -4.0725
Max Act: 3.4781. Min Act: -0.1700
Data Index: 6702103 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0725. Min Range: -4.0725
Max Act: 3.4781. Min Act: -0.1700
Data Index: 5487167 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0725. Min Range: -4.0725
Max Act: 3.4781. Min Act: -0.1700
Data Index: 2655865 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0725. Min Range: -4.0725
Max Act: 3.4781. Min Act: -0.1700
Data Index: 3432656 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0725. Min Range: -4.0725
Max Act: 3.4624. Min Act: -0.1700
Data Index: 1020443 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19