Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2211 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1420. Min Act: -0.0001

Data Index: 387026 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1481. Min Act: -0.0001

Data Index: 753268 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1271. Min Act: -0.0001

Data Index: 362461 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1536. Min Act: -0.0001

Data Index: 1184527 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1352. Min Act: -0.0001

Data Index: 1300107 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1361. Min Act: -0.0001

Data Index: 1043101 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1353. Min Act: -0.0001

Data Index: 1133466 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1311. Min Act: -0.0001

Data Index: 1009727 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1238. Min Act: -0.0001

Data Index: 262 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1366. Min Act: -0.0001

Data Index: 213591 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1274. Min Act: -0.0001

Data Index: 478242 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1267. Min Act: -0.0001

Data Index: 876987 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1128. Min Act: -0.0001

Data Index: 197701 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1141. Min Act: -0.0001

Data Index: 432029 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1208. Min Act: -0.0001

Data Index: 465 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1310. Min Act: -0.0001

Data Index: 1230282 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1148. Min Act: -0.0001

Data Index: 1193279 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1134. Min Act: -0.0001

Data Index: 1193100 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1159. Min Act: -0.0001

Data Index: 1149763 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1163. Min Act: -0.0001

Data Index: 36125 (C4 (Web Text))

Max Activating Token Index: 670