Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1522 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6411. Min Range: -6.6411
Max Act: 6.6411. Min Act: -0.1700
Data Index: 6926418 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6411. Min Range: -6.6411
Max Act: 6.6411. Min Act: -0.1700
Data Index: 2675123 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6411. Min Range: -6.6411
Max Act: 6.6411. Min Act: -0.1700
Data Index: 1548714 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6411. Min Range: -6.6411
Max Act: 6.5161. Min Act: -0.1700
Data Index: 3414586 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6411. Min Range: -6.6411
Max Act: 6.4849. Min Act: -0.1700
Data Index: 1778873 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6411. Min Range: -6.6411
Max Act: 6.4224. Min Act: -0.1700
Data Index: 7377016 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6411. Min Range: -6.6411
Max Act: 6.3911. Min Act: -0.1700
Data Index: 6246751 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6411. Min Range: -6.6411
Max Act: 6.3599. Min Act: -0.1700
Data Index: 8429784 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6411. Min Range: -6.6411
Max Act: 6.3599. Min Act: -0.1700
Data Index: 1754416 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6411. Min Range: -6.6411
Max Act: 6.3286. Min Act: -0.1700
Data Index: 3006965 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6411. Min Range: -6.6411
Max Act: 6.3286. Min Act: -0.1700
Data Index: 2335487 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6411. Min Range: -6.6411
Max Act: 6.2661. Min Act: -0.1700
Data Index: 1862412 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6411. Min Range: -6.6411
Max Act: 6.2349. Min Act: -0.1700
Data Index: 425417 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6411. Min Range: -6.6411
Max Act: 6.2349. Min Act: -0.1700
Data Index: 2131569 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6411. Min Range: -6.6411
Max Act: 6.2036. Min Act: -0.1700
Data Index: 6060024 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6411. Min Range: -6.6411
Max Act: 6.2036. Min Act: -0.1700
Data Index: 3895154 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6411. Min Range: -6.6411
Max Act: 6.2036. Min Act: -0.1700
Data Index: 628044 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6411. Min Range: -6.6411
Max Act: 6.2036. Min Act: -0.1700
Data Index: 422796 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6411. Min Range: -6.6411
Max Act: 6.1724. Min Act: -0.1700
Data Index: 4159563 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6411. Min Range: -6.6411
Max Act: 6.1724. Min Act: -0.1700
Data Index: 3016061 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19