Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2078 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.9437. Min Range: -1.9437
Max Act: 1.9437. Min Act: -0.0001
Data Index: 976205 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9437. Min Range: -1.9437
Max Act: 1.8260. Min Act: -0.0001
Data Index: 990797 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9437. Min Range: -1.9437
Max Act: 1.7807. Min Act: -0.0001
Data Index: 484035 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9437. Min Range: -1.9437
Max Act: 1.6533. Min Act: -0.0001
Data Index: 1016606 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9437. Min Range: -1.9437
Max Act: 1.6602. Min Act: -0.0001
Data Index: 871636 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9437. Min Range: -1.9437
Max Act: 1.6925. Min Act: -0.0001
Data Index: 393191 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9437. Min Range: -1.9437
Max Act: 1.5687. Min Act: -0.0001
Data Index: 745858 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9437. Min Range: -1.9437
Max Act: 1.5529. Min Act: -0.0001
Data Index: 1314053 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9437. Min Range: -1.9437
Max Act: 1.5476. Min Act: -0.0001
Data Index: 285678 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9437. Min Range: -1.9437
Max Act: 1.6336. Min Act: -0.0001
Data Index: 1308462 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9437. Min Range: -1.9437
Max Act: 1.5729. Min Act: -0.0001
Data Index: 1025884 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9437. Min Range: -1.9437
Max Act: 1.4813. Min Act: -0.0001
Data Index: 712669 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9437. Min Range: -1.9437
Max Act: 1.4867. Min Act: -0.0001
Data Index: 467658 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9437. Min Range: -1.9437
Max Act: 1.4321. Min Act: -0.0001
Data Index: 1021451 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9437. Min Range: -1.9437
Max Act: 1.4665. Min Act: -0.0001
Data Index: 465775 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9437. Min Range: -1.9437
Max Act: 1.5005. Min Act: -0.0001
Data Index: 439775 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9437. Min Range: -1.9437
Max Act: 1.4559. Min Act: -0.0001
Data Index: 1341040 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9437. Min Range: -1.9437
Max Act: 1.5347. Min Act: -0.0001
Data Index: 972373 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9437. Min Range: -1.9437
Max Act: 1.4461. Min Act: -0.0001
Data Index: 102973 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9437. Min Range: -1.9437
Max Act: 1.5218. Min Act: -0.0001
Data Index: 1094548 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19