Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4554 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.7257. Min Act: -0.0000

Data Index: 282178 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.5337. Min Act: -0.0000

Data Index: 813294 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.2712. Min Act: -0.0000

Data Index: 1086662 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.1341. Min Act: -0.0000

Data Index: 560323 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.0355. Min Act: -0.0000

Data Index: 1188009 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 1.7257. Min Range: -1.7257

Max Act: 0.9845. Min Act: -0.0000

Data Index: 936494 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.1336. Min Act: -0.0000

Data Index: 497683 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.0193. Min Act: -0.0000

Data Index: 1251179 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 1.7257. Min Range: -1.7257

Max Act: 0.9933. Min Act: -0.0000

Data Index: 385145 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 1.7257. Min Range: -1.7257

Max Act: 0.9320. Min Act: -0.0000

Data Index: 1078826 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.0088. Min Act: -0.0000

Data Index: 604060 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 1.7257. Min Range: -1.7257

Max Act: 0.8959. Min Act: -0.0000

Data Index: 805397 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 1.7257. Min Range: -1.7257

Max Act: 0.8509. Min Act: -0.0000

Data Index: 1329369 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 1.7257. Min Range: -1.7257

Max Act: 0.8020. Min Act: -0.0000

Data Index: 425458 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 1.7257. Min Range: -1.7257

Max Act: 0.9111. Min Act: -0.0000

Data Index: 1213781 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 1.7257. Min Range: -1.7257

Max Act: 0.8795. Min Act: -0.0000

Data Index: 123693 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 1.7257. Min Range: -1.7257

Max Act: 0.8428. Min Act: -0.0000

Data Index: 1304730 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 1.7257. Min Range: -1.7257

Max Act: 0.7845. Min Act: -0.0000

Data Index: 420190 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 1.7257. Min Range: -1.7257

Max Act: 0.8552. Min Act: -0.0000

Data Index: 282163 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 1.7257. Min Range: -1.7257

Max Act: 0.8236. Min Act: -0.0000

Data Index: 951506 (C4 (Web Text))

Max Activating Token Index: 348