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

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

Neuron 5999 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.9272. Min Act: -0.0000

Data Index: 1287331 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.7760. Min Act: -0.0000

Data Index: 1297495 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.8388. Min Act: -0.0000

Data Index: 647261 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.6822. Min Act: -0.0000

Data Index: 851376 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.5200. Min Act: -0.0000

Data Index: 1179665 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.4283. Min Act: -0.0000

Data Index: 139779 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.6634. Min Act: -0.0000

Data Index: 916014 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.5566. Min Act: -0.0000

Data Index: 399497 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.5502. Min Act: -0.0000

Data Index: 196688 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.5130. Min Act: -0.0000

Data Index: 1038303 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.5974. Min Act: -0.0000

Data Index: 293317 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.4162. Min Act: -0.0000

Data Index: 1183983 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.4096. Min Act: -0.0000

Data Index: 494529 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.3935. Min Act: -0.0000

Data Index: 790241 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.3801. Min Act: -0.0000

Data Index: 941465 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.6229. Min Act: -0.0000

Data Index: 196307 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.2428. Min Act: -0.0000

Data Index: 1288972 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.3443. Min Act: -0.0000

Data Index: 124074 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.2294. Min Act: -0.0000

Data Index: 1191113 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.2029. Min Act: -0.0000

Data Index: 830603 (C4 (Web Text))

Max Activating Token Index: 205