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

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

Neuron 1041 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1566. Min Act: -0.0001

Data Index: 713891 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1544. Min Act: -0.0001

Data Index: 934399 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1362. Min Act: -0.0001

Data Index: 633987 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1330. Min Act: -0.0000

Data Index: 458420 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1109528 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1268. Min Act: -0.0001

Data Index: 701909 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1312. Min Act: -0.0001

Data Index: 1046671 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1312. Min Act: -0.0001

Data Index: 1189277 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1323. Min Act: -0.0001

Data Index: 291885 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1287. Min Act: -0.0001

Data Index: 617128 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1267. Min Act: -0.0001

Data Index: 1291771 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1253. Min Act: -0.0001

Data Index: 852991 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1223. Min Act: -0.0001

Data Index: 543657 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1181. Min Act: -0.0001

Data Index: 413309 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1172. Min Act: -0.0001

Data Index: 700919 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1132981 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1145485 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1237. Min Act: -0.0001

Data Index: 88216 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1139. Min Act: -0.0001

Data Index: 744385 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1174. Min Act: -0.0001

Data Index: 1065563 (C4 (Web Text))

Max Activating Token Index: 659