Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1808 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.6745. Min Range: -2.6745
Max Act: 2.6745. Min Act: -0.0001
Data Index: 50710 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6745. Min Range: -2.6745
Max Act: 2.3080. Min Act: -0.0001
Data Index: 539197 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6745. Min Range: -2.6745
Max Act: 2.3177. Min Act: -0.0001
Data Index: 578261 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6745. Min Range: -2.6745
Max Act: 2.2236. Min Act: -0.0001
Data Index: 1123588 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6745. Min Range: -2.6745
Max Act: 2.0761. Min Act: -0.0001
Data Index: 1108937 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6745. Min Range: -2.6745
Max Act: 2.2303. Min Act: -0.0001
Data Index: 56432 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6745. Min Range: -2.6745
Max Act: 2.1130. Min Act: -0.0001
Data Index: 586666 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6745. Min Range: -2.6745
Max Act: 2.0746. Min Act: -0.0001
Data Index: 1010759 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6745. Min Range: -2.6745
Max Act: 2.0988. Min Act: -0.0001
Data Index: 517436 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6745. Min Range: -2.6745
Max Act: 2.0862. Min Act: -0.0001
Data Index: 844132 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6745. Min Range: -2.6745
Max Act: 1.9585. Min Act: -0.0001
Data Index: 292204 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6745. Min Range: -2.6745
Max Act: 2.0648. Min Act: -0.0001
Data Index: 276179 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6745. Min Range: -2.6745
Max Act: 1.9359. Min Act: -0.0001
Data Index: 888348 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6745. Min Range: -2.6745
Max Act: 2.0395. Min Act: -0.0001
Data Index: 561929 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6745. Min Range: -2.6745
Max Act: 2.0800. Min Act: -0.0001
Data Index: 1361939 (Python Code)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6745. Min Range: -2.6745
Max Act: 2.1583. Min Act: -0.0001
Data Index: 845031 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6745. Min Range: -2.6745
Max Act: 2.1474. Min Act: -0.0001
Data Index: 11914 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6745. Min Range: -2.6745
Max Act: 1.9562. Min Act: -0.0001
Data Index: 1195290 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6745. Min Range: -2.6745
Max Act: 1.9769. Min Act: -0.0001
Data Index: 101964 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6745. Min Range: -2.6745
Max Act: 2.0894. Min Act: -0.0001
Data Index: 808377 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19