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

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

Neuron 2066 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.5169. Min Act: -0.0001

Data Index: 1435984 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.5066. Min Act: -0.0002

Data Index: 849243 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.5128. Min Act: -0.0001

Data Index: 403197 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4614. Min Act: -0.0002

Data Index: 204393 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4242. Min Act: -0.0002

Data Index: 515320 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4350. Min Act: -0.0002

Data Index: 585692 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4110. Min Act: -0.0001

Data Index: 1256172 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4083. Min Act: -0.0001

Data Index: 656198 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4078. Min Act: -0.0001

Data Index: 675302 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4233. Min Act: -0.0002

Data Index: 1001003 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4344. Min Act: -0.0002

Data Index: 861694 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3821. Min Act: -0.0001

Data Index: 735213 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4279. Min Act: -0.0002

Data Index: 708837 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4028. Min Act: -0.0002

Data Index: 800109 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3853. Min Act: -0.0001

Data Index: 880526 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3897. Min Act: -0.0001

Data Index: 822778 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3977. Min Act: -0.0002

Data Index: 1137908 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4111. Min Act: -0.0001

Data Index: 738527 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4241. Min Act: -0.0002

Data Index: 821734 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4209. Min Act: -0.0002

Data Index: 373683 (C4 (Web Text))

Max Activating Token Index: 749