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

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

Neuron 4021 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2132. Min Range: -1.2132

Max Act: 1.2132. Min Act: -0.0001

Data Index: 1402689 (Python Code)

Max Activating Token Index: 1014

Text #1

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.8859. Min Act: -0.0001

Data Index: 63794 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.8426. Min Act: -0.0001

Data Index: 1420093 (Python Code)

Max Activating Token Index: 97

Text #3

Max Range: 1.2132. Min Range: -1.2132

Max Act: 1.0084. Min Act: -0.0000

Data Index: 658729 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.8649. Min Act: -0.0000

Data Index: 639240 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.8483. Min Act: -0.0000

Data Index: 1142718 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.8271. Min Act: -0.0000

Data Index: 1038609 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.7655. Min Act: -0.0000

Data Index: 228898 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.8044. Min Act: -0.0000

Data Index: 509438 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.7454. Min Act: -0.0001

Data Index: 1457158 (Python Code)

Max Activating Token Index: 398

Text #10

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.7372. Min Act: -0.0001

Data Index: 146787 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.7010. Min Act: -0.0001

Data Index: 1437983 (Python Code)

Max Activating Token Index: 216

Text #12

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.7496. Min Act: -0.0000

Data Index: 539038 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.7526. Min Act: -0.0000

Data Index: 835958 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.7101. Min Act: -0.0000

Data Index: 225887 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.6761. Min Act: -0.0000

Data Index: 428292 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.6960. Min Act: -0.0000

Data Index: 1096546 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1356496 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1585650 (Python Code)

Max Activating Token Index: 781

Text #19

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.7129. Min Act: -0.0000

Data Index: 892225 (C4 (Web Text))

Max Activating Token Index: 461