Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6382 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3362. Min Range: -6.3362
Max Act: 6.3362. Min Act: -0.1700
Data Index: 2346611 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.6800. Min Act: -0.1700
Data Index: 5037438 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.6800. Min Act: -0.1700
Data Index: 5127200 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.6487. Min Act: -0.1700
Data Index: 2804961 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.5862. Min Act: -0.1700
Data Index: 4672740 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.5550. Min Act: -0.1700
Data Index: 3457706 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.5550. Min Act: -0.1700
Data Index: 4856263 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.5550. Min Act: -0.1700
Data Index: 609903 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.5237. Min Act: -0.1700
Data Index: 3053960 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.5237. Min Act: -0.1700
Data Index: 1949509 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.4925. Min Act: -0.1700
Data Index: 1787384 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.5237. Min Act: -0.1700
Data Index: 8617270 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.4300. Min Act: -0.1700
Data Index: 5445398 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.4612. Min Act: -0.1700
Data Index: 3512131 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.4612. Min Act: -0.1700
Data Index: 7429041 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.4300. Min Act: -0.1700
Data Index: 2443843 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.4925. Min Act: -0.1700
Data Index: 295165 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.4612. Min Act: -0.1700
Data Index: 729227 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.3987. Min Act: -0.1700
Data Index: 1525762 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.3987. Min Act: -0.1700
Data Index: 3163014 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19