Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4491 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.8059. Min Act: -0.0001
Data Index: 1317824 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.5567. Min Act: -0.0001
Data Index: 88515 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.4702. Min Act: -0.0001
Data Index: 519550 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.5865. Min Act: -0.0001
Data Index: 260935 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.5303. Min Act: -0.0001
Data Index: 1141537 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.3933. Min Act: -0.0001
Data Index: 208893 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.2518. Min Act: -0.0001
Data Index: 226371 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.1220. Min Act: -0.0001
Data Index: 951306 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.1751. Min Act: -0.0001
Data Index: 166986 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.0395. Min Act: -0.0001
Data Index: 842320 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.2031. Min Act: -0.0001
Data Index: 472921 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8059. Min Range: -2.8059
Max Act: 1.9385. Min Act: -0.0001
Data Index: 9767 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8059. Min Range: -2.8059
Max Act: 1.9617. Min Act: -0.0001
Data Index: 122030 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8059. Min Range: -2.8059
Max Act: 2.1683. Min Act: -0.0001
Data Index: 273593 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8059. Min Range: -2.8059
Max Act: 1.9196. Min Act: -0.0001
Data Index: 124315 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8059. Min Range: -2.8059
Max Act: 1.9144. Min Act: -0.0001
Data Index: 682508 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8059. Min Range: -2.8059
Max Act: 1.7633. Min Act: -0.0001
Data Index: 718728 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8059. Min Range: -2.8059
Max Act: 1.7589. Min Act: -0.0001
Data Index: 1164512 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8059. Min Range: -2.8059
Max Act: 1.8552. Min Act: -0.0001
Data Index: 1248387 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8059. Min Range: -2.8059
Max Act: 1.9362. Min Act: -0.0001
Data Index: 791678 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19