Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5109 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.4886. Min Range: -1.4886
Max Act: 1.4886. Min Act: -0.0001
Data Index: 100854 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4886. Min Range: -1.4886
Max Act: 1.2953. Min Act: -0.0001
Data Index: 1105217 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4886. Min Range: -1.4886
Max Act: 1.3703. Min Act: -0.0001
Data Index: 1404335 (Python Code)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4886. Min Range: -1.4886
Max Act: 1.2387. Min Act: -0.0001
Data Index: 1150157 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4886. Min Range: -1.4886
Max Act: 1.2629. Min Act: -0.0001
Data Index: 37182 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4886. Min Range: -1.4886
Max Act: 1.2910. Min Act: -0.0001
Data Index: 1192439 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4886. Min Range: -1.4886
Max Act: 1.3345. Min Act: -0.0001
Data Index: 478817 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4886. Min Range: -1.4886
Max Act: 1.1841. Min Act: -0.0001
Data Index: 1033122 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4886. Min Range: -1.4886
Max Act: 1.2365. Min Act: -0.0001
Data Index: 158760 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4886. Min Range: -1.4886
Max Act: 1.2494. Min Act: -0.0001
Data Index: 1028490 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4886. Min Range: -1.4886
Max Act: 1.0725. Min Act: -0.0001
Data Index: 67223 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4886. Min Range: -1.4886
Max Act: 1.0465. Min Act: -0.0001
Data Index: 96431 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4886. Min Range: -1.4886
Max Act: 1.1931. Min Act: -0.0001
Data Index: 276495 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4886. Min Range: -1.4886
Max Act: 1.1539. Min Act: -0.0001
Data Index: 1027376 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4886. Min Range: -1.4886
Max Act: 1.2897. Min Act: -0.0001
Data Index: 643822 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4886. Min Range: -1.4886
Max Act: 1.2084. Min Act: -0.0001
Data Index: 785202 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4886. Min Range: -1.4886
Max Act: 1.1742. Min Act: -0.0001
Data Index: 713732 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4886. Min Range: -1.4886
Max Act: 1.2640. Min Act: -0.0001
Data Index: 859028 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4886. Min Range: -1.4886
Max Act: 1.1532. Min Act: -0.0001
Data Index: 1555502 (Python Code)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4886. Min Range: -1.4886
Max Act: 1.0820. Min Act: -0.0001
Data Index: 338240 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19