Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1211 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1494. Min Act: -0.0006

Data Index: 1200354 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1342. Min Act: -0.0006

Data Index: 141888 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1287. Min Act: -0.0006

Data Index: 368185 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1240. Min Act: -0.0006

Data Index: 97317 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1286. Min Act: -0.0006

Data Index: 829535 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1175. Min Act: -0.0006

Data Index: 215056 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1244. Min Act: -0.0006

Data Index: 773150 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1227. Min Act: -0.0006

Data Index: 346634 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1214. Min Act: -0.0006

Data Index: 581175 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1121. Min Act: -0.0006

Data Index: 771391 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1208. Min Act: -0.0005

Data Index: 591249 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1244. Min Act: -0.0006

Data Index: 109723 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1148. Min Act: -0.0006

Data Index: 108461 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1188. Min Act: -0.0006

Data Index: 252329 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1145. Min Act: -0.0006

Data Index: 563686 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1227. Min Act: -0.0006

Data Index: 494947 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1186. Min Act: -0.0006

Data Index: 1019780 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1131. Min Act: -0.0006

Data Index: 1301092 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1169. Min Act: -0.0006

Data Index: 652468 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1158. Min Act: -0.0006

Data Index: 512171 (C4 (Web Text))

Max Activating Token Index: 570