Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3608 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7428. Min Range: -7.7428
Max Act: 7.7428. Min Act: -0.1700
Data Index: 8299977 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7428. Min Range: -7.7428
Max Act: 7.4303. Min Act: -0.1700
Data Index: 4756662 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7428. Min Range: -7.7428
Max Act: 7.2428. Min Act: -0.1700
Data Index: 830190 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7428. Min Range: -7.7428
Max Act: 7.2116. Min Act: -0.1700
Data Index: 8730554 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7428. Min Range: -7.7428
Max Act: 7.1178. Min Act: -0.1700
Data Index: 648818 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7428. Min Range: -7.7428
Max Act: 7.0241. Min Act: -0.1700
Data Index: 8330797 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7428. Min Range: -7.7428
Max Act: 6.9303. Min Act: -0.1700
Data Index: 1525958 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7428. Min Range: -7.7428
Max Act: 6.9303. Min Act: -0.1700
Data Index: 4073510 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7428. Min Range: -7.7428
Max Act: 6.8053. Min Act: -0.1700
Data Index: 1510213 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7428. Min Range: -7.7428
Max Act: 6.8053. Min Act: -0.1700
Data Index: 5408223 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7428. Min Range: -7.7428
Max Act: 6.8053. Min Act: -0.1700
Data Index: 7729068 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7428. Min Range: -7.7428
Max Act: 6.8053. Min Act: -0.1700
Data Index: 279339 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7428. Min Range: -7.7428
Max Act: 6.8053. Min Act: -0.1700
Data Index: 6057002 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7428. Min Range: -7.7428
Max Act: 6.7428. Min Act: -0.1700
Data Index: 5458515 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7428. Min Range: -7.7428
Max Act: 6.7116. Min Act: -0.1700
Data Index: 6896992 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7428. Min Range: -7.7428
Max Act: 6.7116. Min Act: -0.1700
Data Index: 3472214 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7428. Min Range: -7.7428
Max Act: 6.6803. Min Act: -0.1700
Data Index: 6334406 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7428. Min Range: -7.7428
Max Act: 6.6491. Min Act: -0.1700
Data Index: 5853757 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7428. Min Range: -7.7428
Max Act: 6.6178. Min Act: -0.1700
Data Index: 4118180 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7428. Min Range: -7.7428
Max Act: 6.6178. Min Act: -0.1700
Data Index: 5017378 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19