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

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

Neuron 2207 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8489. Min Range: -1.8489

Max Act: 1.8489. Min Act: -0.0001

Data Index: 637285 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 1.8489. Min Range: -1.8489

Max Act: 1.6138. Min Act: -0.0000

Data Index: 1130161 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 1.8489. Min Range: -1.8489

Max Act: 1.4393. Min Act: -0.0000

Data Index: 1209004 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 1.8489. Min Range: -1.8489

Max Act: 1.3650. Min Act: -0.0000

Data Index: 1251843 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 1.8489. Min Range: -1.8489

Max Act: 1.3585. Min Act: -0.0000

Data Index: 90814 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 1.8489. Min Range: -1.8489

Max Act: 1.2260. Min Act: -0.0000

Data Index: 241766 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 1.8489. Min Range: -1.8489

Max Act: 1.2705. Min Act: -0.0001

Data Index: 1244000 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 1.8489. Min Range: -1.8489

Max Act: 1.2153. Min Act: -0.0000

Data Index: 1268049 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 1.8489. Min Range: -1.8489

Max Act: 1.2415. Min Act: -0.0000

Data Index: 1316780 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 1.8489. Min Range: -1.8489

Max Act: 1.2099. Min Act: -0.0000

Data Index: 1065406 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 1.8489. Min Range: -1.8489

Max Act: 1.1112. Min Act: -0.0000

Data Index: 1296262 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 1.8489. Min Range: -1.8489

Max Act: 1.2749. Min Act: -0.0000

Data Index: 1129566 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 1.8489. Min Range: -1.8489

Max Act: 1.1870. Min Act: -0.0000

Data Index: 797425 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 1.8489. Min Range: -1.8489

Max Act: 1.2193. Min Act: -0.0000

Data Index: 1016655 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 1.8489. Min Range: -1.8489

Max Act: 1.0979. Min Act: -0.0000

Data Index: 832778 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 1.8489. Min Range: -1.8489

Max Act: 1.0634. Min Act: -0.0000

Data Index: 639119 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 1.8489. Min Range: -1.8489

Max Act: 1.0808. Min Act: -0.0000

Data Index: 121050 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 1.8489. Min Range: -1.8489

Max Act: 1.0753. Min Act: -0.0000

Data Index: 1152898 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 1.8489. Min Range: -1.8489

Max Act: 0.9884. Min Act: -0.0001

Data Index: 6338 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 1.8489. Min Range: -1.8489

Max Act: 1.0439. Min Act: -0.0000

Data Index: 470819 (C4 (Web Text))

Max Activating Token Index: 431