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

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

Neuron 253 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1298. Min Range: -4.1298

Max Act: 4.1298. Min Act: -0.0000

Data Index: 219187 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 4.1298. Min Range: -4.1298

Max Act: 3.7517. Min Act: -0.0000

Data Index: 987198 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 4.1298. Min Range: -4.1298

Max Act: 3.8035. Min Act: -0.0000

Data Index: 206714 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 4.1298. Min Range: -4.1298

Max Act: 3.3846. Min Act: -0.0000

Data Index: 1344286 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 4.1298. Min Range: -4.1298

Max Act: 3.3977. Min Act: -0.0000

Data Index: 1045546 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 4.1298. Min Range: -4.1298

Max Act: 3.2019. Min Act: -0.0000

Data Index: 456209 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 4.1298. Min Range: -4.1298

Max Act: 3.0041. Min Act: -0.0000

Data Index: 739233 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 4.1298. Min Range: -4.1298

Max Act: 3.0149. Min Act: -0.0000

Data Index: 635493 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 4.1298. Min Range: -4.1298

Max Act: 2.6014. Min Act: -0.0000

Data Index: 659968 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 4.1298. Min Range: -4.1298

Max Act: 2.9901. Min Act: -0.0000

Data Index: 479158 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 4.1298. Min Range: -4.1298

Max Act: 2.8476. Min Act: -0.0000

Data Index: 487476 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 4.1298. Min Range: -4.1298

Max Act: 2.8397. Min Act: -0.0000

Data Index: 1195339 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 4.1298. Min Range: -4.1298

Max Act: 2.5800. Min Act: -0.0000

Data Index: 1272288 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 4.1298. Min Range: -4.1298

Max Act: 2.5655. Min Act: -0.0000

Data Index: 899962 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 4.1298. Min Range: -4.1298

Max Act: 2.6685. Min Act: -0.0000

Data Index: 918019 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 4.1298. Min Range: -4.1298

Max Act: 2.6850. Min Act: -0.0000

Data Index: 992235 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 4.1298. Min Range: -4.1298

Max Act: 2.6681. Min Act: -0.0000

Data Index: 940048 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 4.1298. Min Range: -4.1298

Max Act: 2.6465. Min Act: -0.0000

Data Index: 672795 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 4.1298. Min Range: -4.1298

Max Act: 2.7816. Min Act: -0.0000

Data Index: 715647 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 4.1298. Min Range: -4.1298

Max Act: 2.6104. Min Act: -0.0000

Data Index: 1033460 (C4 (Web Text))

Max Activating Token Index: 87