Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 592 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0303. Min Act: -0.0001

Data Index: 1213175 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0320. Min Act: -0.0001

Data Index: 449114 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0271. Min Act: -0.0001

Data Index: 708069 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0293. Min Act: -0.0001

Data Index: 1053578 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0290. Min Act: -0.0001

Data Index: 529078 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0241. Min Act: -0.0001

Data Index: 1069919 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0241. Min Act: -0.0001

Data Index: 515031 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0239. Min Act: -0.0001

Data Index: 366911 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0239. Min Act: -0.0001

Data Index: 648785 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0233. Min Act: -0.0001

Data Index: 185878 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0238. Min Act: -0.0001

Data Index: 96749 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0222. Min Act: -0.0001

Data Index: 398871 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0222. Min Act: -0.0001

Data Index: 979351 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0216. Min Act: -0.0001

Data Index: 1310504 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0235. Min Act: -0.0001

Data Index: 732811 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0259. Min Act: -0.0001

Data Index: 106685 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0205. Min Act: -0.0001

Data Index: 943538 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0224. Min Act: -0.0001

Data Index: 1099256 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0216. Min Act: -0.0001

Data Index: 718108 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0223. Min Act: -0.0001

Data Index: 66001 (C4 (Web Text))

Max Activating Token Index: 604