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

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

Neuron 4062 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: 0.1647. Min Range: -0.1647

Max Act: 0.1647. Min Act: -0.0001

Data Index: 436896 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1524. Min Act: -0.0001

Data Index: 124788 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1546. Min Act: -0.0001

Data Index: 321150 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1431. Min Act: -0.0001

Data Index: 1173132 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1286. Min Act: -0.0001

Data Index: 924007 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1328. Min Act: -0.0001

Data Index: 1319822 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1221. Min Act: -0.0001

Data Index: 1125462 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1266. Min Act: -0.0001

Data Index: 628004 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1255. Min Act: -0.0001

Data Index: 846184 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1200. Min Act: -0.0001

Data Index: 707691 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1289. Min Act: -0.0001

Data Index: 878080 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1237. Min Act: -0.0001

Data Index: 573030 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1081. Min Act: -0.0001

Data Index: 1193282 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1201. Min Act: -0.0001

Data Index: 370693 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1202. Min Act: -0.0001

Data Index: 1084091 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1155. Min Act: -0.0001

Data Index: 184363 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1152. Min Act: -0.0001

Data Index: 83809 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1352563 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1238. Min Act: -0.0001

Data Index: 409924 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1190. Min Act: -0.0001

Data Index: 1054636 (C4 (Web Text))

Max Activating Token Index: 400