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

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

Neuron 1474 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: 0.1529. Min Range: -0.1529

Max Act: 0.1529. Min Act: -0.0001

Data Index: 752878 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1442. Min Act: -0.0002

Data Index: 1021711 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1336. Min Act: -0.0002

Data Index: 1342239 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1271. Min Act: -0.0002

Data Index: 99953 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1173. Min Act: -0.0002

Data Index: 1357530 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1225. Min Act: -0.0002

Data Index: 26047 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1229. Min Act: -0.0001

Data Index: 970992 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1178. Min Act: -0.0001

Data Index: 573316 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1199. Min Act: -0.0002

Data Index: 1243571 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1169. Min Act: -0.0002

Data Index: 1017089 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1179. Min Act: -0.0002

Data Index: 731090 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1123. Min Act: -0.0002

Data Index: 880279 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1155. Min Act: -0.0001

Data Index: 709675 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1197. Min Act: -0.0001

Data Index: 199542 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1162. Min Act: 0.0000

Data Index: 843349 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1104. Min Act: -0.0001

Data Index: 860851 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1135. Min Act: -0.0002

Data Index: 720219 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1128. Min Act: 0.0000

Data Index: 93677 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1262005 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1115. Min Act: -0.0001

Data Index: 901755 (C4 (Web Text))

Max Activating Token Index: 1022