Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3128 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0272. Min Act: -0.0003

Data Index: 610985 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1178631 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0260. Min Act: -0.0003

Data Index: 318729 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0295. Min Act: -0.0003

Data Index: 181932 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0264. Min Act: -0.0003

Data Index: 352533 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0240. Min Act: -0.0004

Data Index: 171280 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0267. Min Act: -0.0003

Data Index: 126940 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0254. Min Act: -0.0003

Data Index: 729348 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0242. Min Act: -0.0003

Data Index: 259351 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0264. Min Act: -0.0003

Data Index: 224662 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0249. Min Act: -0.0003

Data Index: 894673 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0259. Min Act: -0.0003

Data Index: 1122518 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0248. Min Act: -0.0003

Data Index: 980446 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0249. Min Act: -0.0003

Data Index: 451159 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0238. Min Act: -0.0003

Data Index: 858563 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0236. Min Act: -0.0003

Data Index: 150143 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0219. Min Act: -0.0003

Data Index: 492979 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0262. Min Act: -0.0003

Data Index: 518151 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0253. Min Act: -0.0003

Data Index: 94724 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0263. Min Act: -0.0003

Data Index: 55349 (C4 (Web Text))

Max Activating Token Index: 761