Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 6105 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.0248. Min Range: -2.0248
Max Act: 1.9656. Min Act: -0.0001
Data Index: 846566 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0248. Min Range: -2.0248
Max Act: 2.0248. Min Act: -0.0001
Data Index: 1161869 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0248. Min Range: -2.0248
Max Act: 1.9068. Min Act: -0.0001
Data Index: 920058 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0248. Min Range: -2.0248
Max Act: 1.8943. Min Act: -0.0001
Data Index: 1043882 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0248. Min Range: -2.0248
Max Act: 1.8826. Min Act: -0.0001
Data Index: 617518 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0248. Min Range: -2.0248
Max Act: 1.9297. Min Act: -0.0001
Data Index: 1226358 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0248. Min Range: -2.0248
Max Act: 2.0118. Min Act: -0.0001
Data Index: 574771 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0248. Min Range: -2.0248
Max Act: 1.9797. Min Act: -0.0001
Data Index: 1290199 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0248. Min Range: -2.0248
Max Act: 1.8549. Min Act: -0.0001
Data Index: 578049 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0248. Min Range: -2.0248
Max Act: 1.7314. Min Act: -0.0001
Data Index: 889813 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0248. Min Range: -2.0248
Max Act: 1.8474. Min Act: -0.0001
Data Index: 362166 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0248. Min Range: -2.0248
Max Act: 1.7729. Min Act: -0.0001
Data Index: 726328 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0248. Min Range: -2.0248
Max Act: 1.7880. Min Act: -0.0001
Data Index: 1252394 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0248. Min Range: -2.0248
Max Act: 1.7745. Min Act: -0.0001
Data Index: 760696 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0248. Min Range: -2.0248
Max Act: 1.6499. Min Act: -0.0001
Data Index: 187953 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0248. Min Range: -2.0248
Max Act: 1.6911. Min Act: -0.0001
Data Index: 1241556 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0248. Min Range: -2.0248
Max Act: 1.9345. Min Act: -0.0001
Data Index: 1241516 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0248. Min Range: -2.0248
Max Act: 1.7209. Min Act: -0.0001
Data Index: 891103 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0248. Min Range: -2.0248
Max Act: 1.7257. Min Act: -0.0001
Data Index: 945335 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0248. Min Range: -2.0248
Max Act: 1.5982. Min Act: -0.0001
Data Index: 495952 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19