Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3678. Min Range: -6.3678
Max Act: 6.3678. Min Act: -0.1700
Data Index: 4208820 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3678. Min Range: -6.3678
Max Act: 6.3365. Min Act: -0.1700
Data Index: 198553 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3678. Min Range: -6.3678
Max Act: 6.3053. Min Act: -0.1700
Data Index: 198552 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3678. Min Range: -6.3678
Max Act: 6.1490. Min Act: -0.1700
Data Index: 4901165 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3678. Min Range: -6.3678
Max Act: 6.1178. Min Act: -0.1700
Data Index: 1974222 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3678. Min Range: -6.3678
Max Act: 6.0553. Min Act: -0.1700
Data Index: 7686475 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3678. Min Range: -6.3678
Max Act: 5.9928. Min Act: -0.1700
Data Index: 1676634 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3678. Min Range: -6.3678
Max Act: 5.9928. Min Act: -0.1700
Data Index: 198571 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3678. Min Range: -6.3678
Max Act: 5.9615. Min Act: -0.1700
Data Index: 6976793 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3678. Min Range: -6.3678
Max Act: 5.8678. Min Act: -0.1700
Data Index: 3706906 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3678. Min Range: -6.3678
Max Act: 5.8990. Min Act: -0.1700
Data Index: 198542 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3678. Min Range: -6.3678
Max Act: 5.8678. Min Act: -0.1700
Data Index: 6114319 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3678. Min Range: -6.3678
Max Act: 5.8365. Min Act: -0.1700
Data Index: 390404 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3678. Min Range: -6.3678
Max Act: 5.8365. Min Act: -0.1700
Data Index: 692236 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3678. Min Range: -6.3678
Max Act: 5.8365. Min Act: -0.1700
Data Index: 3196674 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3678. Min Range: -6.3678
Max Act: 5.8365. Min Act: -0.1700
Data Index: 4578757 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3678. Min Range: -6.3678
Max Act: 5.7740. Min Act: -0.1700
Data Index: 75057 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3678. Min Range: -6.3678
Max Act: 5.7740. Min Act: -0.1700
Data Index: 921238 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3678. Min Range: -6.3678
Max Act: 5.7428. Min Act: -0.1700
Data Index: 3679613 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3678. Min Range: -6.3678
Max Act: 5.7115. Min Act: -0.1700
Data Index: 6949719 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19