Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3506 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2310. Min Range: -6.2310
Max Act: 6.2310. Min Act: -0.1700
Data Index: 268415 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2310. Min Range: -6.2310
Max Act: 6.2310. Min Act: -0.1700
Data Index: 6729707 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2310. Min Range: -6.2310
Max Act: 6.1685. Min Act: -0.1700
Data Index: 2387240 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2310. Min Range: -6.2310
Max Act: 6.1373. Min Act: -0.1700
Data Index: 6866281 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2310. Min Range: -6.2310
Max Act: 6.1060. Min Act: -0.1700
Data Index: 7838278 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2310. Min Range: -6.2310
Max Act: 5.9498. Min Act: -0.1700
Data Index: 4029920 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2310. Min Range: -6.2310
Max Act: 5.9498. Min Act: -0.1700
Data Index: 2060730 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2310. Min Range: -6.2310
Max Act: 5.8873. Min Act: -0.1700
Data Index: 2987648 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2310. Min Range: -6.2310
Max Act: 5.8248. Min Act: -0.1700
Data Index: 5310613 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2310. Min Range: -6.2310
Max Act: 5.8248. Min Act: -0.1700
Data Index: 8001968 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2310. Min Range: -6.2310
Max Act: 5.8560. Min Act: -0.1700
Data Index: 1992306 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2310. Min Range: -6.2310
Max Act: 5.8248. Min Act: -0.1700
Data Index: 856952 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2310. Min Range: -6.2310
Max Act: 5.7935. Min Act: -0.1700
Data Index: 4997948 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2310. Min Range: -6.2310
Max Act: 5.7623. Min Act: -0.1700
Data Index: 2349855 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2310. Min Range: -6.2310
Max Act: 5.7623. Min Act: -0.1700
Data Index: 1371635 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2310. Min Range: -6.2310
Max Act: 5.7310. Min Act: -0.1700
Data Index: 4303749 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2310. Min Range: -6.2310
Max Act: 5.7310. Min Act: -0.1700
Data Index: 1099677 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2310. Min Range: -6.2310
Max Act: 5.7310. Min Act: -0.1700
Data Index: 7253903 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2310. Min Range: -6.2310
Max Act: 5.7310. Min Act: -0.1700
Data Index: 4254454 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2310. Min Range: -6.2310
Max Act: 5.6998. Min Act: -0.1700
Data Index: 2983602 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19