Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2512 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.2246. Min Act: -0.0001

Data Index: 1302060 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.2129. Min Act: -0.0001

Data Index: 370089 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.2183. Min Act: -0.0001

Data Index: 74562 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.2253. Min Act: -0.0001

Data Index: 100002 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.2175. Min Act: -0.0001

Data Index: 699188 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.2236. Min Act: -0.0001

Data Index: 527172 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.2158. Min Act: -0.0001

Data Index: 168669 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.2232. Min Act: -0.0001

Data Index: 296933 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.2152. Min Act: -0.0001

Data Index: 738979 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.2160. Min Act: -0.0001

Data Index: 1300368 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.2141. Min Act: -0.0001

Data Index: 482765 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.2096. Min Act: -0.0001

Data Index: 574855 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.2071. Min Act: -0.0001

Data Index: 74588 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.2130. Min Act: -0.0001

Data Index: 1154531 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.2145. Min Act: -0.0001

Data Index: 1063854 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.2055. Min Act: -0.0001

Data Index: 1100883 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.2105. Min Act: -0.0001

Data Index: 857557 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.1970. Min Act: -0.0001

Data Index: 578667 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.2042. Min Act: -0.0001

Data Index: 245256 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 0.2253. Min Range: -0.2253

Max Act: 0.2027. Min Act: -0.0001

Data Index: 1014918 (C4 (Web Text))

Max Activating Token Index: 167