Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3090 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.5555. Min Act: -0.0001
Data Index: 1322209 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.3235. Min Act: -0.0001
Data Index: 450040 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5555. Min Range: -2.5555
Max Act: 1.8966. Min Act: -0.0001
Data Index: 1084082 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5555. Min Range: -2.5555
Max Act: 1.8345. Min Act: -0.0001
Data Index: 982001 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5555. Min Range: -2.5555
Max Act: 1.9228. Min Act: -0.0001
Data Index: 861293 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5555. Min Range: -2.5555
Max Act: 1.7733. Min Act: -0.0001
Data Index: 508754 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5555. Min Range: -2.5555
Max Act: 1.2160. Min Act: -0.0001
Data Index: 1330229 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5555. Min Range: -2.5555
Max Act: 1.2623. Min Act: -0.0001
Data Index: 93939 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5555. Min Range: -2.5555
Max Act: 1.3294. Min Act: -0.0001
Data Index: 898347 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5555. Min Range: -2.5555
Max Act: 1.1279. Min Act: -0.0001
Data Index: 1310491 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5555. Min Range: -2.5555
Max Act: 1.1884. Min Act: -0.0001
Data Index: 818257 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5555. Min Range: -2.5555
Max Act: 1.2301. Min Act: -0.0001
Data Index: 1228849 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5555. Min Range: -2.5555
Max Act: 1.0473. Min Act: -0.0001
Data Index: 579110 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5555. Min Range: -2.5555
Max Act: 1.0656. Min Act: -0.0001
Data Index: 787378 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5555. Min Range: -2.5555
Max Act: 1.0817. Min Act: -0.0001
Data Index: 978571 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5555. Min Range: -2.5555
Max Act: 0.9869. Min Act: -0.0001
Data Index: 948283 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5555. Min Range: -2.5555
Max Act: 0.9650. Min Act: -0.0001
Data Index: 963424 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5555. Min Range: -2.5555
Max Act: 1.0204. Min Act: -0.0001
Data Index: 1274315 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5555. Min Range: -2.5555
Max Act: 1.0363. Min Act: -0.0001
Data Index: 1022444 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5555. Min Range: -2.5555
Max Act: 1.0095. Min Act: -0.0001
Data Index: 291782 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19