Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3649 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.7222. Min Range: -1.7222
Max Act: 1.7222. Min Act: -0.0001
Data Index: 296049 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7222. Min Range: -1.7222
Max Act: 1.4924. Min Act: -0.0001
Data Index: 97015 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7222. Min Range: -1.7222
Max Act: 1.3751. Min Act: -0.0001
Data Index: 796887 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7222. Min Range: -1.7222
Max Act: 1.4513. Min Act: -0.0001
Data Index: 402029 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7222. Min Range: -1.7222
Max Act: 1.3772. Min Act: -0.0001
Data Index: 53529 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7222. Min Range: -1.7222
Max Act: 1.3483. Min Act: -0.0001
Data Index: 978908 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7222. Min Range: -1.7222
Max Act: 1.2955. Min Act: -0.0001
Data Index: 46945 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7222. Min Range: -1.7222
Max Act: 1.4041. Min Act: -0.0001
Data Index: 716549 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7222. Min Range: -1.7222
Max Act: 1.3069. Min Act: -0.0001
Data Index: 1308792 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7222. Min Range: -1.7222
Max Act: 1.2592. Min Act: -0.0001
Data Index: 515725 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7222. Min Range: -1.7222
Max Act: 1.3005. Min Act: -0.0001
Data Index: 1307832 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7222. Min Range: -1.7222
Max Act: 1.2900. Min Act: -0.0001
Data Index: 1003385 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7222. Min Range: -1.7222
Max Act: 1.2279. Min Act: -0.0001
Data Index: 551136 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7222. Min Range: -1.7222
Max Act: 1.2785. Min Act: -0.0001
Data Index: 1157713 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7222. Min Range: -1.7222
Max Act: 1.2880. Min Act: -0.0001
Data Index: 430472 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7222. Min Range: -1.7222
Max Act: 1.2392. Min Act: -0.0001
Data Index: 1309635 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7222. Min Range: -1.7222
Max Act: 1.2742. Min Act: -0.0001
Data Index: 1186270 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7222. Min Range: -1.7222
Max Act: 1.2730. Min Act: -0.0001
Data Index: 822372 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7222. Min Range: -1.7222
Max Act: 1.1957. Min Act: -0.0001
Data Index: 1345323 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7222. Min Range: -1.7222
Max Act: 1.1215. Min Act: -0.0001
Data Index: 936499 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19