Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 62 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7434. Min Range: -6.7434
Max Act: 6.7434. Min Act: -0.1700
Data Index: 5178654 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7434. Min Range: -6.7434
Max Act: 6.6184. Min Act: -0.1700
Data Index: 6211974 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7434. Min Range: -6.7434
Max Act: 6.5247. Min Act: -0.1700
Data Index: 968391 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7434. Min Range: -6.7434
Max Act: 6.4309. Min Act: -0.1700
Data Index: 3586265 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7434. Min Range: -6.7434
Max Act: 6.3997. Min Act: -0.1700
Data Index: 5801540 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7434. Min Range: -6.7434
Max Act: 6.3684. Min Act: -0.1700
Data Index: 4762081 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7434. Min Range: -6.7434
Max Act: 6.2434. Min Act: -0.1700
Data Index: 302565 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7434. Min Range: -6.7434
Max Act: 6.2747. Min Act: -0.1700
Data Index: 7092469 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7434. Min Range: -6.7434
Max Act: 6.2434. Min Act: -0.1700
Data Index: 5015515 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7434. Min Range: -6.7434
Max Act: 6.2434. Min Act: -0.1700
Data Index: 8150105 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7434. Min Range: -6.7434
Max Act: 6.2434. Min Act: -0.1700
Data Index: 3667740 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7434. Min Range: -6.7434
Max Act: 6.2434. Min Act: -0.1700
Data Index: 1906491 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7434. Min Range: -6.7434
Max Act: 6.2434. Min Act: -0.1700
Data Index: 6343914 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7434. Min Range: -6.7434
Max Act: 6.2122. Min Act: -0.1700
Data Index: 6383385 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7434. Min Range: -6.7434
Max Act: 6.2122. Min Act: -0.1700
Data Index: 36553 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7434. Min Range: -6.7434
Max Act: 6.1497. Min Act: -0.1700
Data Index: 6997348 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7434. Min Range: -6.7434
Max Act: 6.1809. Min Act: -0.1700
Data Index: 5153669 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7434. Min Range: -6.7434
Max Act: 6.1809. Min Act: -0.1700
Data Index: 4607994 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7434. Min Range: -6.7434
Max Act: 6.1184. Min Act: -0.1700
Data Index: 5347948 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7434. Min Range: -6.7434
Max Act: 6.1497. Min Act: -0.1700
Data Index: 6623455 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19