Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3277 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1542. Min Act: -0.0002

Data Index: 898869 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1236. Min Act: -0.0002

Data Index: 88759 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1236. Min Act: -0.0002

Data Index: 830349 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1212. Min Act: -0.0002

Data Index: 135944 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1142. Min Act: -0.0002

Data Index: 167510 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1236. Min Act: -0.0002

Data Index: 538939 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1279. Min Act: -0.0002

Data Index: 139262 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1187. Min Act: -0.0002

Data Index: 355549 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1148. Min Act: -0.0002

Data Index: 1301909 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1192. Min Act: -0.0002

Data Index: 1308240 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1111. Min Act: -0.0002

Data Index: 444988 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1054. Min Act: -0.0002

Data Index: 1232018 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1048. Min Act: -0.0002

Data Index: 946004 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1122. Min Act: -0.0002

Data Index: 1171845 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1157. Min Act: -0.0002

Data Index: 484020 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1084. Min Act: -0.0002

Data Index: 594806 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1064. Min Act: -0.0002

Data Index: 448843 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1022. Min Act: -0.0002

Data Index: 147568 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1050. Min Act: -0.0002

Data Index: 441719 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1006. Min Act: -0.0002

Data Index: 1023671 (C4 (Web Text))

Max Activating Token Index: 244