Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1773 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.4378. Min Act: -0.0002
Data Index: 912613 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.4200. Min Act: -0.0001
Data Index: 1086739 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.4040. Min Act: -0.0001
Data Index: 392369 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3803. Min Act: -0.0001
Data Index: 447739 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3657. Min Act: -0.0001
Data Index: 71812 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3417. Min Act: -0.0001
Data Index: 1236825 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3538. Min Act: -0.0002
Data Index: 330300 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3568. Min Act: -0.0001
Data Index: 1004903 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3321. Min Act: -0.0002
Data Index: 741998 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3535. Min Act: -0.0001
Data Index: 1514146 (Python Code)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3451. Min Act: -0.0002
Data Index: 784330 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3571. Min Act: -0.0001
Data Index: 1462940 (Python Code)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3325. Min Act: -0.0001
Data Index: 900506 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3286. Min Act: -0.0001
Data Index: 711906 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3105. Min Act: -0.0001
Data Index: 576422 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3268. Min Act: -0.0001
Data Index: 1406499 (Python Code)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3385. Min Act: -0.0001
Data Index: 844950 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3272. Min Act: -0.0002
Data Index: 110408 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3176. Min Act: -0.0001
Data Index: 1500682 (Python Code)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3168. Min Act: -0.0001
Data Index: 56398 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19