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

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

Neuron 4091 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.4214. Min Act: -0.0001

Data Index: 790229 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3858. Min Act: -0.0001

Data Index: 248487 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.2758. Min Act: -0.0001

Data Index: 315580 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3496. Min Act: -0.0001

Data Index: 482449 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3076. Min Act: -0.0001

Data Index: 1014210 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3267. Min Act: -0.0001

Data Index: 517637 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3293. Min Act: -0.0001

Data Index: 763563 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3047. Min Act: -0.0001

Data Index: 1039381 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3113. Min Act: -0.0001

Data Index: 472674 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3104. Min Act: -0.0001

Data Index: 874603 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3130. Min Act: -0.0001

Data Index: 443232 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.2928. Min Act: -0.0001

Data Index: 1333212 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3103. Min Act: -0.0001

Data Index: 1248693 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3162. Min Act: -0.0001

Data Index: 30905 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.2953. Min Act: -0.0001

Data Index: 605745 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.2979. Min Act: -0.0001

Data Index: 708244 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.2881. Min Act: -0.0001

Data Index: 1297975 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3042. Min Act: -0.0001

Data Index: 425163 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.2660. Min Act: -0.0001

Data Index: 1090458 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.2802. Min Act: -0.0001

Data Index: 831202 (C4 (Web Text))

Max Activating Token Index: 407