Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0098. Min Range: -8.0098
Max Act: 8.0098. Min Act: -0.1700
Data Index: 5805642 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0098. Min Range: -8.0098
Max Act: 7.8223. Min Act: -0.1700
Data Index: 2675995 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0098. Min Range: -8.0098
Max Act: 7.6348. Min Act: -0.1700
Data Index: 8542899 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0098. Min Range: -8.0098
Max Act: 7.6348. Min Act: -0.1700
Data Index: 2169994 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0098. Min Range: -8.0098
Max Act: 7.5098. Min Act: -0.1700
Data Index: 3670538 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0098. Min Range: -8.0098
Max Act: 7.4473. Min Act: -0.1700
Data Index: 8430332 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0098. Min Range: -8.0098
Max Act: 7.4473. Min Act: -0.1700
Data Index: 4391017 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0098. Min Range: -8.0098
Max Act: 7.4160. Min Act: -0.1700
Data Index: 560000 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0098. Min Range: -8.0098
Max Act: 7.4160. Min Act: -0.1700
Data Index: 7886015 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0098. Min Range: -8.0098
Max Act: 7.4160. Min Act: -0.1700
Data Index: 8767982 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0098. Min Range: -8.0098
Max Act: 7.3848. Min Act: -0.1700
Data Index: 1603691 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0098. Min Range: -8.0098
Max Act: 7.3848. Min Act: -0.1700
Data Index: 8123339 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0098. Min Range: -8.0098
Max Act: 7.3535. Min Act: -0.1700
Data Index: 4207436 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0098. Min Range: -8.0098
Max Act: 7.3535. Min Act: -0.1700
Data Index: 3519573 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0098. Min Range: -8.0098
Max Act: 7.3223. Min Act: -0.1700
Data Index: 4399618 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0098. Min Range: -8.0098
Max Act: 7.3223. Min Act: -0.1700
Data Index: 4707744 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0098. Min Range: -8.0098
Max Act: 7.2910. Min Act: -0.1700
Data Index: 24614 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0098. Min Range: -8.0098
Max Act: 7.3223. Min Act: -0.1700
Data Index: 7389620 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0098. Min Range: -8.0098
Max Act: 7.2910. Min Act: -0.1700
Data Index: 7399334 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0098. Min Range: -8.0098
Max Act: 7.2598. Min Act: -0.1700
Data Index: 3047791 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19