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

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

Neuron 31 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.9960. Min Act: -0.0001

Data Index: 341659 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.8124. Min Act: -0.0000

Data Index: 689144 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.8598. Min Act: -0.0000

Data Index: 859292 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.7832. Min Act: -0.0001

Data Index: 186797 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.7483. Min Act: -0.0000

Data Index: 906042 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.7467. Min Act: -0.0000

Data Index: 435120 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.7235. Min Act: -0.0001

Data Index: 1246736 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.7674. Min Act: -0.0000

Data Index: 508848 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.7038. Min Act: -0.0001

Data Index: 485790 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1358022 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.7161. Min Act: -0.0000

Data Index: 305651 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.7112. Min Act: -0.0000

Data Index: 605767 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.6797. Min Act: -0.0000

Data Index: 1356126 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.7003. Min Act: -0.0001

Data Index: 1195738 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.6813. Min Act: -0.0000

Data Index: 68805 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.7053. Min Act: -0.0001

Data Index: 171644 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.6993. Min Act: -0.0000

Data Index: 370250 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1183211 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.7198. Min Act: -0.0000

Data Index: 293493 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1097625 (C4 (Web Text))

Max Activating Token Index: 304