Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3603 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7140. Min Range: -2.7140
Max Act: 2.7140. Min Act: -0.1700
Data Index: 3851306 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7140. Min Range: -2.7140
Max Act: 2.7140. Min Act: -0.1700
Data Index: 2260853 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7140. Min Range: -2.7140
Max Act: 2.7140. Min Act: -0.1700
Data Index: 3647524 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7140. Min Range: -2.7140
Max Act: 2.6660. Min Act: -0.1700
Data Index: 7560770 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7140. Min Range: -2.7140
Max Act: 2.5856. Min Act: -0.1700
Data Index: 6963688 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7140. Min Range: -2.7140
Max Act: 2.5695. Min Act: -0.1700
Data Index: 2298217 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7140. Min Range: -2.7140
Max Act: 2.5372. Min Act: -0.1700
Data Index: 766276 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7140. Min Range: -2.7140
Max Act: 2.5372. Min Act: -0.1700
Data Index: 5324844 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7140. Min Range: -2.7140
Max Act: 2.5372. Min Act: -0.1700
Data Index: 1076904 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7140. Min Range: -2.7140
Max Act: 2.5372. Min Act: -0.1700
Data Index: 600173 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7140. Min Range: -2.7140
Max Act: 2.5372. Min Act: -0.1700
Data Index: 5315454 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7140. Min Range: -2.7140
Max Act: 2.5372. Min Act: -0.1700
Data Index: 5284148 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7140. Min Range: -2.7140
Max Act: 2.5372. Min Act: -0.1700
Data Index: 4801191 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7140. Min Range: -2.7140
Max Act: 2.5372. Min Act: -0.1700
Data Index: 8735512 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7140. Min Range: -2.7140
Max Act: 2.5211. Min Act: -0.1700
Data Index: 5966818 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7140. Min Range: -2.7140
Max Act: 2.5211. Min Act: -0.1700
Data Index: 8184006 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7140. Min Range: -2.7140
Max Act: 2.5049. Min Act: -0.1700
Data Index: 28292 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7140. Min Range: -2.7140
Max Act: 2.5049. Min Act: -0.1700
Data Index: 1121372 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7140. Min Range: -2.7140
Max Act: 2.5049. Min Act: -0.1700
Data Index: 4106448 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7140. Min Range: -2.7140
Max Act: 2.4887. Min Act: -0.1700
Data Index: 6313405 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19