Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1897 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.0365. Min Range: -2.0365
Max Act: 2.0365. Min Act: -0.0001
Data Index: 1125215 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0365. Min Range: -2.0365
Max Act: 1.6982. Min Act: -0.0001
Data Index: 1477729 (Python Code)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0365. Min Range: -2.0365
Max Act: 1.6493. Min Act: -0.0001
Data Index: 1598807 (Python Code)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0365. Min Range: -2.0365
Max Act: 1.5524. Min Act: -0.0001
Data Index: 1159506 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0365. Min Range: -2.0365
Max Act: 1.5785. Min Act: -0.0001
Data Index: 712954 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0365. Min Range: -2.0365
Max Act: 1.6636. Min Act: -0.0001
Data Index: 1626728 (Python Code)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0365. Min Range: -2.0365
Max Act: 1.4778. Min Act: -0.0001
Data Index: 1240468 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0365. Min Range: -2.0365
Max Act: 1.6447. Min Act: -0.0001
Data Index: 1647900 (Python Code)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0365. Min Range: -2.0365
Max Act: 1.4892. Min Act: -0.0001
Data Index: 1614337 (Python Code)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0365. Min Range: -2.0365
Max Act: 1.4383. Min Act: -0.0001
Data Index: 1254222 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0365. Min Range: -2.0365
Max Act: 1.5932. Min Act: -0.0001
Data Index: 282714 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0365. Min Range: -2.0365
Max Act: 1.5195. Min Act: -0.0001
Data Index: 59867 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0365. Min Range: -2.0365
Max Act: 1.4739. Min Act: -0.0001
Data Index: 1056457 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0365. Min Range: -2.0365
Max Act: 1.5509. Min Act: -0.0001
Data Index: 1477549 (Python Code)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0365. Min Range: -2.0365
Max Act: 1.4164. Min Act: -0.0001
Data Index: 1453527 (Python Code)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0365. Min Range: -2.0365
Max Act: 1.5387. Min Act: -0.0001
Data Index: 1395358 (Python Code)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0365. Min Range: -2.0365
Max Act: 1.5375. Min Act: -0.0001
Data Index: 122706 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0365. Min Range: -2.0365
Max Act: 1.4691. Min Act: -0.0001
Data Index: 850873 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0365. Min Range: -2.0365
Max Act: 1.5179. Min Act: -0.0001
Data Index: 985433 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0365. Min Range: -2.0365
Max Act: 1.2431. Min Act: -0.0001
Data Index: 898442 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19