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

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

Neuron 4194 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.4209. Min Act: -0.0000

Data Index: 903533 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3903. Min Act: -0.0000

Data Index: 565384 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3274. Min Act: -0.0000

Data Index: 816795 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3321. Min Act: -0.0000

Data Index: 423562 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3133. Min Act: 0.0000

Data Index: 1129641 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3149. Min Act: -0.0000

Data Index: 1078428 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3213. Min Act: -0.0000

Data Index: 216132 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3312. Min Act: 0.0000

Data Index: 491308 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3191. Min Act: -0.0000

Data Index: 1162901 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3207. Min Act: -0.0000

Data Index: 519975 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2933. Min Act: -0.0000

Data Index: 884781 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2897. Min Act: -0.0000

Data Index: 1182702 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2932. Min Act: -0.0000

Data Index: 282460 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2915. Min Act: -0.0000

Data Index: 1030819 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2892. Min Act: 0.0000

Data Index: 1123110 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2868. Min Act: -0.0000

Data Index: 150542 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2856. Min Act: -0.0000

Data Index: 1214793 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2792. Min Act: -0.0000

Data Index: 384180 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2917. Min Act: -0.0000

Data Index: 1304417 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2832. Min Act: -0.0000

Data Index: 1216928 (C4 (Web Text))

Max Activating Token Index: 968