Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5204 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.2353. Min Range: -2.2353
Max Act: 2.2353. Min Act: -0.0002
Data Index: 531109 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 2.2353. Min Range: -2.2353
Max Act: 2.1005. Min Act: -0.0002
Data Index: 903297 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 2.2353. Min Range: -2.2353
Max Act: 1.7464. Min Act: -0.0002
Data Index: 727552 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 2.2353. Min Range: -2.2353
Max Act: 1.7770. Min Act: -0.0002
Data Index: 1063533 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 2.2353. Min Range: -2.2353
Max Act: 1.7062. Min Act: -0.0002
Data Index: 182549 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 2.2353. Min Range: -2.2353
Max Act: 1.6783. Min Act: -0.0002
Data Index: 310153 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 2.2353. Min Range: -2.2353
Max Act: 1.5539. Min Act: -0.0002
Data Index: 205844 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 2.2353. Min Range: -2.2353
Max Act: 1.6148. Min Act: -0.0002
Data Index: 757964 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 2.2353. Min Range: -2.2353
Max Act: 1.5629. Min Act: -0.0002
Data Index: 9796 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 2.2353. Min Range: -2.2353
Max Act: 1.6305. Min Act: -0.0002
Data Index: 1323197 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 2.2353. Min Range: -2.2353
Max Act: 1.6229. Min Act: -0.0002
Data Index: 393868 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 2.2353. Min Range: -2.2353
Max Act: 1.4875. Min Act: -0.0002
Data Index: 433482 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 2.2353. Min Range: -2.2353
Max Act: 1.5711. Min Act: -0.0002
Data Index: 1322978 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 2.2353. Min Range: -2.2353
Max Act: 1.4542. Min Act: -0.0002
Data Index: 345254 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 2.2353. Min Range: -2.2353
Max Act: 1.5252. Min Act: -0.0002
Data Index: 226727 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 2.2353. Min Range: -2.2353
Max Act: 1.5897. Min Act: -0.0002
Data Index: 998279 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 2.2353. Min Range: -2.2353
Max Act: 1.4495. Min Act: -0.0002
Data Index: 292364 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 2.2353. Min Range: -2.2353
Max Act: 1.4904. Min Act: -0.0002
Data Index: 1027497 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 2.2353. Min Range: -2.2353
Max Act: 1.5309. Min Act: -0.0002
Data Index: 943321 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 2.2353. Min Range: -2.2353
Max Act: 1.4455. Min Act: -0.0002
Data Index: 700283 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full textTruncated
Full Text #19