Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6239. Min Range: -6.6239
Max Act: 6.6239. Min Act: -0.1700
Data Index: 7710373 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6239. Min Range: -6.6239
Max Act: 6.5927. Min Act: -0.1700
Data Index: 2038581 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6239. Min Range: -6.6239
Max Act: 6.4677. Min Act: -0.1700
Data Index: 3667108 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6239. Min Range: -6.6239
Max Act: 6.4364. Min Act: -0.1700
Data Index: 8825039 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6239. Min Range: -6.6239
Max Act: 6.4364. Min Act: -0.1700
Data Index: 2287415 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6239. Min Range: -6.6239
Max Act: 6.4052. Min Act: -0.1700
Data Index: 1784582 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6239. Min Range: -6.6239
Max Act: 6.3739. Min Act: -0.1700
Data Index: 102621 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6239. Min Range: -6.6239
Max Act: 6.3427. Min Act: -0.1700
Data Index: 659422 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6239. Min Range: -6.6239
Max Act: 6.3739. Min Act: -0.1700
Data Index: 7010746 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6239. Min Range: -6.6239
Max Act: 6.3427. Min Act: -0.1700
Data Index: 751444 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6239. Min Range: -6.6239
Max Act: 6.2802. Min Act: -0.1700
Data Index: 2326402 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6239. Min Range: -6.6239
Max Act: 6.3114. Min Act: -0.1700
Data Index: 7738664 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6239. Min Range: -6.6239
Max Act: 6.2489. Min Act: -0.1700
Data Index: 6860466 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6239. Min Range: -6.6239
Max Act: 6.2177. Min Act: -0.1700
Data Index: 6991325 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6239. Min Range: -6.6239
Max Act: 6.2177. Min Act: -0.1700
Data Index: 7556943 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6239. Min Range: -6.6239
Max Act: 6.2177. Min Act: -0.1700
Data Index: 3037759 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6239. Min Range: -6.6239
Max Act: 6.2177. Min Act: -0.1700
Data Index: 5491622 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6239. Min Range: -6.6239
Max Act: 6.2177. Min Act: -0.1700
Data Index: 4794170 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6239. Min Range: -6.6239
Max Act: 6.1864. Min Act: -0.1700
Data Index: 1240329 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6239. Min Range: -6.6239
Max Act: 6.2177. Min Act: -0.1700
Data Index: 1302672 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19