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

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

Neuron 3007 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: 2.5189. Min Range: -2.5189

Max Act: 2.5189. Min Act: 0.0001

Data Index: 424505 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 2.5189. Min Range: -2.5189

Max Act: 2.2516. Min Act: -0.0000

Data Index: 524875 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 2.5189. Min Range: -2.5189

Max Act: 2.0146. Min Act: -0.0000

Data Index: 957329 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 2.5189. Min Range: -2.5189

Max Act: 1.9211. Min Act: -0.0000

Data Index: 712677 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 2.5189. Min Range: -2.5189

Max Act: 1.9043. Min Act: -0.0000

Data Index: 262746 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 2.5189. Min Range: -2.5189

Max Act: 1.7407. Min Act: -0.0000

Data Index: 551347 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 2.5189. Min Range: -2.5189

Max Act: 1.5976. Min Act: -0.0000

Data Index: 366882 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 2.5189. Min Range: -2.5189

Max Act: 1.7697. Min Act: -0.0000

Data Index: 86558 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 2.5189. Min Range: -2.5189

Max Act: 1.7493. Min Act: -0.0000

Data Index: 93703 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 2.5189. Min Range: -2.5189

Max Act: 1.7530. Min Act: -0.0000

Data Index: 339307 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 2.5189. Min Range: -2.5189

Max Act: 1.8103. Min Act: -0.0000

Data Index: 954302 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 2.5189. Min Range: -2.5189

Max Act: 1.6762. Min Act: -0.0000

Data Index: 279943 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 2.5189. Min Range: -2.5189

Max Act: 1.6511. Min Act: -0.0000

Data Index: 761429 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 2.5189. Min Range: -2.5189

Max Act: 1.6554. Min Act: -0.0000

Data Index: 100981 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 2.5189. Min Range: -2.5189

Max Act: 1.6530. Min Act: -0.0000

Data Index: 185188 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 2.5189. Min Range: -2.5189

Max Act: 1.6301. Min Act: -0.0000

Data Index: 219253 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 2.5189. Min Range: -2.5189

Max Act: 1.6259. Min Act: -0.0000

Data Index: 889734 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 2.5189. Min Range: -2.5189

Max Act: 1.6024. Min Act: 0.0000

Data Index: 245138 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 2.5189. Min Range: -2.5189

Max Act: 1.6975. Min Act: -0.0000

Data Index: 1039149 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 2.5189. Min Range: -2.5189

Max Act: 1.5116. Min Act: 0.0000

Data Index: 87411 (C4 (Web Text))

Max Activating Token Index: 746