Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 674 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4797. Min Range: -6.4797
Max Act: 6.4797. Min Act: -0.1700
Data Index: 6321064 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4797. Min Range: -6.4797
Max Act: 6.3235. Min Act: -0.1700
Data Index: 382113 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4797. Min Range: -6.4797
Max Act: 6.2297. Min Act: -0.1700
Data Index: 2436351 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4797. Min Range: -6.4797
Max Act: 6.1985. Min Act: -0.1700
Data Index: 3062011 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4797. Min Range: -6.4797
Max Act: 6.1672. Min Act: -0.1700
Data Index: 815426 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4797. Min Range: -6.4797
Max Act: 6.1672. Min Act: -0.1700
Data Index: 4516757 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4797. Min Range: -6.4797
Max Act: 6.1672. Min Act: -0.1700
Data Index: 2436350 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4797. Min Range: -6.4797
Max Act: 6.1360. Min Act: -0.1700
Data Index: 1891487 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4797. Min Range: -6.4797
Max Act: 6.1360. Min Act: -0.1700
Data Index: 8311476 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4797. Min Range: -6.4797
Max Act: 6.1047. Min Act: -0.1700
Data Index: 1761386 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4797. Min Range: -6.4797
Max Act: 6.0735. Min Act: -0.1700
Data Index: 8223251 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4797. Min Range: -6.4797
Max Act: 6.0735. Min Act: -0.1700
Data Index: 697024 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4797. Min Range: -6.4797
Max Act: 6.0735. Min Act: -0.1700
Data Index: 7118434 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4797. Min Range: -6.4797
Max Act: 6.0422. Min Act: -0.1700
Data Index: 3403735 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4797. Min Range: -6.4797
Max Act: 6.0422. Min Act: -0.1700
Data Index: 1364878 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4797. Min Range: -6.4797
Max Act: 6.0422. Min Act: -0.1700
Data Index: 5421053 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4797. Min Range: -6.4797
Max Act: 6.0422. Min Act: -0.1700
Data Index: 5128432 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4797. Min Range: -6.4797
Max Act: 6.0110. Min Act: -0.1700
Data Index: 2964399 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4797. Min Range: -6.4797
Max Act: 6.0422. Min Act: -0.1700
Data Index: 53672 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4797. Min Range: -6.4797
Max Act: 6.0422. Min Act: -0.1700
Data Index: 6652777 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19