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

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

Neuron 1116 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2890. Min Act: -0.0000

Data Index: 9671 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2506. Min Act: -0.0000

Data Index: 343506 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2120. Min Act: -0.0000

Data Index: 71201 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2283. Min Act: -0.0000

Data Index: 323371 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2366. Min Act: -0.0000

Data Index: 675967 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2214. Min Act: -0.0000

Data Index: 628849 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2291. Min Act: -0.0000

Data Index: 459463 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2286. Min Act: -0.0000

Data Index: 236701 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2106. Min Act: -0.0000

Data Index: 1283584 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2240. Min Act: -0.0000

Data Index: 1014366 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2184. Min Act: -0.0000

Data Index: 211175 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1224355 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1915. Min Act: -0.0000

Data Index: 711648 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2208. Min Act: -0.0000

Data Index: 97769 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2142. Min Act: -0.0000

Data Index: 664952 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1962. Min Act: -0.0000

Data Index: 538893 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2088. Min Act: -0.0000

Data Index: 197667 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2004. Min Act: -0.0000

Data Index: 505246 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2080. Min Act: -0.0000

Data Index: 833723 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2144. Min Act: -0.0000

Data Index: 873670 (C4 (Web Text))

Max Activating Token Index: 130