Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2844 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.0386. Min Range: -2.0386
Max Act: 2.0386. Min Act: -0.0001
Data Index: 497108 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0386. Min Range: -2.0386
Max Act: 1.8890. Min Act: -0.0001
Data Index: 158819 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0386. Min Range: -2.0386
Max Act: 1.9849. Min Act: -0.0001
Data Index: 1067220 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0386. Min Range: -2.0386
Max Act: 1.8802. Min Act: -0.0000
Data Index: 164405 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0386. Min Range: -2.0386
Max Act: 1.8928. Min Act: -0.0001
Data Index: 1323972 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0386. Min Range: -2.0386
Max Act: 1.7847. Min Act: -0.0001
Data Index: 1312881 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0386. Min Range: -2.0386
Max Act: 1.7544. Min Act: -0.0001
Data Index: 1040174 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0386. Min Range: -2.0386
Max Act: 1.8157. Min Act: -0.0001
Data Index: 217223 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0386. Min Range: -2.0386
Max Act: 1.8295. Min Act: -0.0001
Data Index: 201412 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0386. Min Range: -2.0386
Max Act: 1.7062. Min Act: -0.0001
Data Index: 989999 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0386. Min Range: -2.0386
Max Act: 1.7907. Min Act: -0.0001
Data Index: 567558 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0386. Min Range: -2.0386
Max Act: 1.5717. Min Act: -0.0001
Data Index: 649578 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0386. Min Range: -2.0386
Max Act: 1.6141. Min Act: -0.0001
Data Index: 70358 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0386. Min Range: -2.0386
Max Act: 1.7841. Min Act: -0.0001
Data Index: 1260585 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0386. Min Range: -2.0386
Max Act: 1.6861. Min Act: -0.0001
Data Index: 104790 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0386. Min Range: -2.0386
Max Act: 1.7418. Min Act: -0.0001
Data Index: 451907 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0386. Min Range: -2.0386
Max Act: 1.6833. Min Act: -0.0001
Data Index: 125280 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0386. Min Range: -2.0386
Max Act: 1.6432. Min Act: -0.0001
Data Index: 976410 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0386. Min Range: -2.0386
Max Act: 1.6421. Min Act: -0.0001
Data Index: 994704 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0386. Min Range: -2.0386
Max Act: 1.4877. Min Act: -0.0001
Data Index: 581397 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19