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

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

Neuron 4727 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5855. Min Range: -3.5855

Max Act: 3.5855. Min Act: -0.0000

Data Index: 85459 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 3.5855. Min Range: -3.5855

Max Act: 3.0257. Min Act: -0.0000

Data Index: 931748 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 3.5855. Min Range: -3.5855

Max Act: 3.3411. Min Act: -0.0000

Data Index: 1250637 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 3.5855. Min Range: -3.5855

Max Act: 3.1299. Min Act: -0.0000

Data Index: 1155535 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 3.5855. Min Range: -3.5855

Max Act: 2.8319. Min Act: -0.0000

Data Index: 342715 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 3.5855. Min Range: -3.5855

Max Act: 2.7749. Min Act: -0.0000

Data Index: 1251052 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 3.5855. Min Range: -3.5855

Max Act: 2.6254. Min Act: -0.0000

Data Index: 297866 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 3.5855. Min Range: -3.5855

Max Act: 2.7175. Min Act: -0.0000

Data Index: 1210249 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 3.5855. Min Range: -3.5855

Max Act: 2.4453. Min Act: -0.0000

Data Index: 1166198 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 3.5855. Min Range: -3.5855

Max Act: 2.4159. Min Act: -0.0000

Data Index: 333959 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 3.5855. Min Range: -3.5855

Max Act: 2.5202. Min Act: -0.0000

Data Index: 1004561 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 3.5855. Min Range: -3.5855

Max Act: 2.5003. Min Act: -0.0000

Data Index: 914683 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 3.5855. Min Range: -3.5855

Max Act: 2.3571. Min Act: -0.0000

Data Index: 989374 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 3.5855. Min Range: -3.5855

Max Act: 2.3489. Min Act: -0.0000

Data Index: 613695 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 3.5855. Min Range: -3.5855

Max Act: 2.3378. Min Act: -0.0000

Data Index: 1023639 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 3.5855. Min Range: -3.5855

Max Act: 2.6044. Min Act: -0.0000

Data Index: 1275666 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 3.5855. Min Range: -3.5855

Max Act: 2.2959. Min Act: -0.0000

Data Index: 642547 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 3.5855. Min Range: -3.5855

Max Act: 2.2916. Min Act: -0.0000

Data Index: 1206490 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 3.5855. Min Range: -3.5855

Max Act: 2.3998. Min Act: -0.0000

Data Index: 1122861 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 3.5855. Min Range: -3.5855

Max Act: 2.3311. Min Act: -0.0000

Data Index: 576986 (C4 (Web Text))

Max Activating Token Index: 42