Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1985 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5237. Min Range: -5.5237
Max Act: 5.5237. Min Act: -0.1700
Data Index: 2007562 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5237. Min Range: -5.5237
Max Act: 5.4924. Min Act: -0.1700
Data Index: 7727628 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5237. Min Range: -5.5237
Max Act: 5.2424. Min Act: -0.1700
Data Index: 1650559 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5237. Min Range: -5.5237
Max Act: 5.1799. Min Act: -0.1700
Data Index: 622756 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5237. Min Range: -5.5237
Max Act: 5.1174. Min Act: -0.1700
Data Index: 1459251 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5237. Min Range: -5.5237
Max Act: 5.1174. Min Act: -0.1700
Data Index: 7636027 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5237. Min Range: -5.5237
Max Act: 5.0549. Min Act: -0.1700
Data Index: 8629164 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5237. Min Range: -5.5237
Max Act: 5.0237. Min Act: -0.1700
Data Index: 2149427 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5237. Min Range: -5.5237
Max Act: 4.9924. Min Act: -0.1700
Data Index: 8606740 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5237. Min Range: -5.5237
Max Act: 4.9612. Min Act: -0.1700
Data Index: 8800794 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5237. Min Range: -5.5237
Max Act: 4.9299. Min Act: -0.1700
Data Index: 5702206 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5237. Min Range: -5.5237
Max Act: 4.9924. Min Act: -0.1700
Data Index: 7817286 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5237. Min Range: -5.5237
Max Act: 4.9299. Min Act: -0.1700
Data Index: 2346439 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5237. Min Range: -5.5237
Max Act: 4.9299. Min Act: -0.1700
Data Index: 2376119 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5237. Min Range: -5.5237
Max Act: 4.8987. Min Act: -0.1700
Data Index: 4335288 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5237. Min Range: -5.5237
Max Act: 4.9299. Min Act: -0.1700
Data Index: 1380443 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5237. Min Range: -5.5237
Max Act: 4.8674. Min Act: -0.1700
Data Index: 6937873 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5237. Min Range: -5.5237
Max Act: 4.8362. Min Act: -0.1700
Data Index: 785512 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5237. Min Range: -5.5237
Max Act: 4.8362. Min Act: -0.1700
Data Index: 2292447 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5237. Min Range: -5.5237
Max Act: 4.8049. Min Act: -0.1700
Data Index: 4884731 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19