Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 763 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.3294. Min Range: -1.3294
Max Act: 1.3294. Min Act: -0.0001
Data Index: 737575 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3294. Min Range: -1.3294
Max Act: 1.2266. Min Act: -0.0001
Data Index: 688301 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3294. Min Range: -1.3294
Max Act: 1.2196. Min Act: -0.0001
Data Index: 1443010 (Python Code)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3294. Min Range: -1.3294
Max Act: 1.1749. Min Act: -0.0001
Data Index: 1068977 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3294. Min Range: -1.3294
Max Act: 1.1411. Min Act: -0.0001
Data Index: 1172267 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3294. Min Range: -1.3294
Max Act: 1.2236. Min Act: -0.0001
Data Index: 640848 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3294. Min Range: -1.3294
Max Act: 1.1397. Min Act: -0.0001
Data Index: 959584 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3294. Min Range: -1.3294
Max Act: 1.2361. Min Act: -0.0001
Data Index: 1467263 (Python Code)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3294. Min Range: -1.3294
Max Act: 1.1622. Min Act: -0.0001
Data Index: 1019368 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3294. Min Range: -1.3294
Max Act: 1.0084. Min Act: -0.0001
Data Index: 1224737 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3294. Min Range: -1.3294
Max Act: 1.0909. Min Act: -0.0001
Data Index: 42244 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3294. Min Range: -1.3294
Max Act: 1.0990. Min Act: -0.0001
Data Index: 564079 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3294. Min Range: -1.3294
Max Act: 1.1733. Min Act: -0.0001
Data Index: 1244224 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3294. Min Range: -1.3294
Max Act: 1.1480. Min Act: -0.0001
Data Index: 437086 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3294. Min Range: -1.3294
Max Act: 1.1177. Min Act: -0.0001
Data Index: 501172 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3294. Min Range: -1.3294
Max Act: 1.0155. Min Act: -0.0001
Data Index: 855465 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3294. Min Range: -1.3294
Max Act: 1.0883. Min Act: -0.0001
Data Index: 540731 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3294. Min Range: -1.3294
Max Act: 1.0395. Min Act: -0.0001
Data Index: 508272 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3294. Min Range: -1.3294
Max Act: 1.1593. Min Act: -0.0001
Data Index: 1186833 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3294. Min Range: -1.3294
Max Act: 1.0767. Min Act: -0.0001
Data Index: 439952 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19