Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2758 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.2405. Min Range: -1.2405
Max Act: 1.2405. Min Act: -0.0001
Data Index: 1260482 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2405. Min Range: -1.2405
Max Act: 1.1513. Min Act: -0.0001
Data Index: 894873 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2405. Min Range: -1.2405
Max Act: 1.1181. Min Act: -0.0001
Data Index: 850270 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2405. Min Range: -1.2405
Max Act: 1.1880. Min Act: -0.0001
Data Index: 1032306 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2405. Min Range: -1.2405
Max Act: 1.0976. Min Act: -0.0001
Data Index: 376732 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2405. Min Range: -1.2405
Max Act: 1.1183. Min Act: -0.0001
Data Index: 1016187 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2405. Min Range: -1.2405
Max Act: 1.1062. Min Act: -0.0001
Data Index: 437829 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2405. Min Range: -1.2405
Max Act: 0.9753. Min Act: -0.0001
Data Index: 1013594 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2405. Min Range: -1.2405
Max Act: 1.0752. Min Act: -0.0001
Data Index: 1102787 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2405. Min Range: -1.2405
Max Act: 1.0628. Min Act: -0.0001
Data Index: 81955 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2405. Min Range: -1.2405
Max Act: 1.0581. Min Act: -0.0001
Data Index: 349778 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2405. Min Range: -1.2405
Max Act: 1.0287. Min Act: -0.0001
Data Index: 944280 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2405. Min Range: -1.2405
Max Act: 1.0187. Min Act: -0.0001
Data Index: 1353208 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2405. Min Range: -1.2405
Max Act: 0.9960. Min Act: -0.0001
Data Index: 1195466 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2405. Min Range: -1.2405
Max Act: 1.0340. Min Act: -0.0001
Data Index: 771065 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2405. Min Range: -1.2405
Max Act: 1.0202. Min Act: -0.0001
Data Index: 486406 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2405. Min Range: -1.2405
Max Act: 1.0236. Min Act: -0.0001
Data Index: 5314 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2405. Min Range: -1.2405
Max Act: 1.0194. Min Act: -0.0001
Data Index: 775129 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2405. Min Range: -1.2405
Max Act: 1.0669. Min Act: -0.0001
Data Index: 1080160 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2405. Min Range: -1.2405
Max Act: 1.0115. Min Act: -0.0001
Data Index: 197348 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19