Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2870 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1645. Min Act: -0.0001

Data Index: 35690 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1487. Min Act: -0.0001

Data Index: 827057 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1298. Min Act: -0.0001

Data Index: 813547 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1164. Min Act: -0.0001

Data Index: 45872 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1196. Min Act: -0.0001

Data Index: 454868 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1282. Min Act: -0.0001

Data Index: 1241017 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1218. Min Act: -0.0001

Data Index: 1000635 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1103. Min Act: -0.0001

Data Index: 956969 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1210. Min Act: -0.0001

Data Index: 977863 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1169. Min Act: -0.0001

Data Index: 95014 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1168. Min Act: -0.0001

Data Index: 1276730 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1128. Min Act: -0.0001

Data Index: 1030251 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1197. Min Act: -0.0001

Data Index: 710913 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1182. Min Act: -0.0001

Data Index: 124040 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1072. Min Act: -0.0001

Data Index: 438391 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1139. Min Act: -0.0001

Data Index: 158021 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1172. Min Act: -0.0001

Data Index: 111616 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1155. Min Act: -0.0001

Data Index: 965004 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1125. Min Act: -0.0001

Data Index: 106231 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1154. Min Act: -0.0001

Data Index: 610970 (C4 (Web Text))

Max Activating Token Index: 223