Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2948 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.7256. Min Range: -3.7256
Max Act: 3.7256. Min Act: -0.0001
Data Index: 608587 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7256. Min Range: -3.7256
Max Act: 2.9571. Min Act: -0.0001
Data Index: 208153 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7256. Min Range: -3.7256
Max Act: 3.0745. Min Act: -0.0001
Data Index: 499307 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7256. Min Range: -3.7256
Max Act: 3.0214. Min Act: -0.0001
Data Index: 196902 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7256. Min Range: -3.7256
Max Act: 3.0320. Min Act: -0.0001
Data Index: 70695 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7256. Min Range: -3.7256
Max Act: 2.7631. Min Act: -0.0001
Data Index: 1178543 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7256. Min Range: -3.7256
Max Act: 2.5653. Min Act: -0.0001
Data Index: 98 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7256. Min Range: -3.7256
Max Act: 2.5879. Min Act: -0.0001
Data Index: 22367 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7256. Min Range: -3.7256
Max Act: 2.4806. Min Act: -0.0001
Data Index: 343527 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7256. Min Range: -3.7256
Max Act: 2.4844. Min Act: -0.0001
Data Index: 404733 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7256. Min Range: -3.7256
Max Act: 2.5741. Min Act: -0.0001
Data Index: 1355251 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7256. Min Range: -3.7256
Max Act: 2.5005. Min Act: -0.0001
Data Index: 134779 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7256. Min Range: -3.7256
Max Act: 2.3711. Min Act: -0.0001
Data Index: 1285040 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7256. Min Range: -3.7256
Max Act: 2.3518. Min Act: -0.0001
Data Index: 938772 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7256. Min Range: -3.7256
Max Act: 2.4824. Min Act: -0.0001
Data Index: 319211 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7256. Min Range: -3.7256
Max Act: 2.3423. Min Act: -0.0001
Data Index: 490810 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7256. Min Range: -3.7256
Max Act: 2.2473. Min Act: -0.0001
Data Index: 1107369 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7256. Min Range: -3.7256
Max Act: 2.4253. Min Act: -0.0001
Data Index: 452967 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7256. Min Range: -3.7256
Max Act: 2.4003. Min Act: -0.0001
Data Index: 1260753 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7256. Min Range: -3.7256
Max Act: 2.2484. Min Act: -0.0001
Data Index: 305569 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19