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

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

Neuron 1593 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0257. Min Act: -0.0006

Data Index: 443638 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0219. Min Act: -0.0005

Data Index: 1336727 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0220. Min Act: -0.0006

Data Index: 883623 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0219. Min Act: -0.0005

Data Index: 207603 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0212. Min Act: -0.0005

Data Index: 1043374 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0200. Min Act: -0.0005

Data Index: 1032087 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0197. Min Act: -0.0005

Data Index: 57911 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0197. Min Act: -0.0005

Data Index: 547162 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0184. Min Act: -0.0005

Data Index: 292598 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0179. Min Act: -0.0005

Data Index: 783393 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0176. Min Act: -0.0005

Data Index: 1461137 (Python Code)

Max Activating Token Index: 502

Text #11

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0172. Min Act: -0.0005

Data Index: 107732 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0175. Min Act: -0.0005

Data Index: 756391 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0165. Min Act: -0.0005

Data Index: 482393 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0165. Min Act: -0.0005

Data Index: 991072 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0159. Min Act: -0.0005

Data Index: 703033 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0147. Min Act: -0.0006

Data Index: 1036980 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0151. Min Act: -0.0005

Data Index: 1458813 (Python Code)

Max Activating Token Index: 80

Text #18

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0153. Min Act: -0.0005

Data Index: 1386867 (Python Code)

Max Activating Token Index: 649

Text #19

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0149. Min Act: -0.0005

Data Index: 1558000 (Python Code)

Max Activating Token Index: 195