Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 746 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1504. Min Act: -0.0002

Data Index: 737237 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1345. Min Act: -0.0001

Data Index: 198491 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1411. Min Act: -0.0000

Data Index: 321181 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1290. Min Act: -0.0002

Data Index: 620039 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1299. Min Act: -0.0000

Data Index: 1188217 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1229. Min Act: -0.0002

Data Index: 841536 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1303. Min Act: -0.0002

Data Index: 86522 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1254. Min Act: -0.0001

Data Index: 976145 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1236. Min Act: -0.0002

Data Index: 641563 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1204. Min Act: -0.0002

Data Index: 43626 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1191. Min Act: -0.0002

Data Index: 996342 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1167. Min Act: -0.0002

Data Index: 1038938 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1184. Min Act: -0.0002

Data Index: 111014 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1144. Min Act: -0.0002

Data Index: 562202 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1218. Min Act: -0.0001

Data Index: 274718 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1149. Min Act: -0.0001

Data Index: 1196896 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1165. Min Act: -0.0002

Data Index: 970996 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1161. Min Act: -0.0001

Data Index: 662197 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1168. Min Act: -0.0002

Data Index: 614042 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.1504. Min Range: -0.1504

Max Act: 0.1128. Min Act: -0.0002

Data Index: 79414 (C4 (Web Text))

Max Activating Token Index: 735