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

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

Neuron 3996 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: 0.2488. Min Range: -0.2488

Max Act: 0.2488. Min Act: -0.0000

Data Index: 483930 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 0.2488. Min Range: -0.2488

Max Act: 0.2442. Min Act: -0.0000

Data Index: 825844 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 0.2488. Min Range: -0.2488

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1253743 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.2488. Min Range: -0.2488

Max Act: 0.2249. Min Act: -0.0000

Data Index: 169183 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 0.2488. Min Range: -0.2488

Max Act: 0.2077. Min Act: -0.0000

Data Index: 1060054 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.2488. Min Range: -0.2488

Max Act: 0.2312. Min Act: -0.0000

Data Index: 253917 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.2488. Min Range: -0.2488

Max Act: 0.2136. Min Act: -0.0000

Data Index: 422880 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.2488. Min Range: -0.2488

Max Act: 0.2144. Min Act: -0.0000

Data Index: 94332 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.2488. Min Range: -0.2488

Max Act: 0.2152. Min Act: -0.0000

Data Index: 338493 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.2488. Min Range: -0.2488

Max Act: 0.2264. Min Act: -0.0000

Data Index: 721239 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.2488. Min Range: -0.2488

Max Act: 0.2158. Min Act: -0.0000

Data Index: 1319642 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 0.2488. Min Range: -0.2488

Max Act: 0.2001. Min Act: -0.0000

Data Index: 525285 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.2488. Min Range: -0.2488

Max Act: 0.2036. Min Act: -0.0000

Data Index: 928953 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 0.2488. Min Range: -0.2488

Max Act: 0.2113. Min Act: -0.0000

Data Index: 1218079 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 0.2488. Min Range: -0.2488

Max Act: 0.2146. Min Act: -0.0000

Data Index: 960789 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.2488. Min Range: -0.2488

Max Act: 0.2064. Min Act: -0.0000

Data Index: 556271 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 0.2488. Min Range: -0.2488

Max Act: 0.2097. Min Act: -0.0000

Data Index: 1351561 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 0.2488. Min Range: -0.2488

Max Act: 0.1974. Min Act: -0.0000

Data Index: 210199 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.2488. Min Range: -0.2488

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1229507 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.2488. Min Range: -0.2488

Max Act: 0.2092. Min Act: -0.0000

Data Index: 637049 (C4 (Web Text))

Max Activating Token Index: 260