Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4026 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8899. Min Range: -9.8899
Max Act: 9.8899. Min Act: -0.1700
Data Index: 8397234 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8899. Min Range: -9.8899
Max Act: 9.8274. Min Act: -0.1700
Data Index: 441865 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8899. Min Range: -9.8899
Max Act: 9.8274. Min Act: -0.1700
Data Index: 3651429 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8899. Min Range: -9.8899
Max Act: 9.8274. Min Act: -0.1700
Data Index: 4260224 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8899. Min Range: -9.8899
Max Act: 9.7649. Min Act: -0.1700
Data Index: 7914941 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8899. Min Range: -9.8899
Max Act: 9.6399. Min Act: -0.1700
Data Index: 7119470 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8899. Min Range: -9.8899
Max Act: 9.5149. Min Act: -0.1700
Data Index: 3898190 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8899. Min Range: -9.8899
Max Act: 9.4524. Min Act: -0.1700
Data Index: 1606656 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8899. Min Range: -9.8899
Max Act: 9.4524. Min Act: -0.1700
Data Index: 1903510 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8899. Min Range: -9.8899
Max Act: 9.4524. Min Act: -0.1700
Data Index: 7191405 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8899. Min Range: -9.8899
Max Act: 9.5149. Min Act: -0.1700
Data Index: 1842693 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8899. Min Range: -9.8899
Max Act: 9.4524. Min Act: -0.1700
Data Index: 4632352 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8899. Min Range: -9.8899
Max Act: 9.4524. Min Act: -0.1700
Data Index: 973267 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8899. Min Range: -9.8899
Max Act: 9.3899. Min Act: -0.1700
Data Index: 2332488 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8899. Min Range: -9.8899
Max Act: 9.3274. Min Act: -0.1700
Data Index: 6959214 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8899. Min Range: -9.8899
Max Act: 9.3899. Min Act: -0.1700
Data Index: 8696414 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8899. Min Range: -9.8899
Max Act: 9.3274. Min Act: -0.1700
Data Index: 1653982 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8899. Min Range: -9.8899
Max Act: 9.3274. Min Act: -0.1700
Data Index: 1051707 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8899. Min Range: -9.8899
Max Act: 9.2649. Min Act: -0.1700
Data Index: 6885834 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8899. Min Range: -9.8899
Max Act: 9.2649. Min Act: -0.1700
Data Index: 3691827 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19