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

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

Neuron 4407 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4210. Min Range: -1.4210

Max Act: 1.4210. Min Act: -0.0000

Data Index: 472893 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 1.4210. Min Range: -1.4210

Max Act: 1.4153. Min Act: -0.0000

Data Index: 1079750 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 1.4210. Min Range: -1.4210

Max Act: 1.3772. Min Act: -0.0000

Data Index: 854379 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 1.4210. Min Range: -1.4210

Max Act: 1.1377. Min Act: -0.0000

Data Index: 688694 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 1.4210. Min Range: -1.4210

Max Act: 1.1661. Min Act: -0.0000

Data Index: 983054 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 1.4210. Min Range: -1.4210

Max Act: 1.1428. Min Act: -0.0000

Data Index: 828094 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 1.4210. Min Range: -1.4210

Max Act: 1.0858. Min Act: -0.0000

Data Index: 369215 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 1.4210. Min Range: -1.4210

Max Act: 1.0278. Min Act: -0.0000

Data Index: 1247301 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 1.4210. Min Range: -1.4210

Max Act: 0.9137. Min Act: -0.0000

Data Index: 1236441 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 1.4210. Min Range: -1.4210

Max Act: 0.9119. Min Act: -0.0000

Data Index: 1152880 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 1.4210. Min Range: -1.4210

Max Act: 0.9179. Min Act: -0.0000

Data Index: 220469 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 1.4210. Min Range: -1.4210

Max Act: 0.8926. Min Act: -0.0000

Data Index: 211739 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 1.4210. Min Range: -1.4210

Max Act: 0.8574. Min Act: -0.0000

Data Index: 905751 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 1.4210. Min Range: -1.4210

Max Act: 0.8787. Min Act: -0.0000

Data Index: 667228 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 1.4210. Min Range: -1.4210

Max Act: 0.8617. Min Act: -0.0000

Data Index: 961093 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 1.4210. Min Range: -1.4210

Max Act: 0.8498. Min Act: -0.0000

Data Index: 342887 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 1.4210. Min Range: -1.4210

Max Act: 0.8572. Min Act: -0.0000

Data Index: 905134 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 1.4210. Min Range: -1.4210

Max Act: 0.7298. Min Act: -0.0000

Data Index: 673621 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 1.4210. Min Range: -1.4210

Max Act: 0.8239. Min Act: -0.0000

Data Index: 498254 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 1.4210. Min Range: -1.4210

Max Act: 0.7929. Min Act: -0.0000

Data Index: 108294 (C4 (Web Text))

Max Activating Token Index: 633