Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5307 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.2374. Min Range: -6.2374

Max Act: 6.2374. Min Act: -0.0001

Data Index: 1115026 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 6.2374. Min Range: -6.2374

Max Act: 5.7090. Min Act: -0.0001

Data Index: 1052081 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 6.2374. Min Range: -6.2374

Max Act: 5.0012. Min Act: -0.0001

Data Index: 265478 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 6.2374. Min Range: -6.2374

Max Act: 4.6846. Min Act: -0.0000

Data Index: 791987 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 6.2374. Min Range: -6.2374

Max Act: 4.3849. Min Act: -0.0000

Data Index: 896493 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 6.2374. Min Range: -6.2374

Max Act: 3.9590. Min Act: -0.0000

Data Index: 963971 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 6.2374. Min Range: -6.2374

Max Act: 3.9447. Min Act: -0.0000

Data Index: 1280072 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 6.2374. Min Range: -6.2374

Max Act: 3.6793. Min Act: -0.0001

Data Index: 829262 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 6.2374. Min Range: -6.2374

Max Act: 3.7596. Min Act: -0.0001

Data Index: 127988 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 6.2374. Min Range: -6.2374

Max Act: 3.6023. Min Act: -0.0001

Data Index: 1056341 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 6.2374. Min Range: -6.2374

Max Act: 3.5163. Min Act: -0.0000

Data Index: 252151 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 6.2374. Min Range: -6.2374

Max Act: 3.7632. Min Act: -0.0000

Data Index: 273602 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 6.2374. Min Range: -6.2374

Max Act: 3.5986. Min Act: -0.0001

Data Index: 21674 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 6.2374. Min Range: -6.2374

Max Act: 3.2642. Min Act: -0.0000

Data Index: 562393 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 6.2374. Min Range: -6.2374

Max Act: 3.3592. Min Act: -0.0001

Data Index: 98808 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 6.2374. Min Range: -6.2374

Max Act: 3.0825. Min Act: -0.0001

Data Index: 1199302 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 6.2374. Min Range: -6.2374

Max Act: 3.0971. Min Act: -0.0001

Data Index: 574147 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 6.2374. Min Range: -6.2374

Max Act: 2.7547. Min Act: -0.0001

Data Index: 635283 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 6.2374. Min Range: -6.2374

Max Act: 2.6831. Min Act: -0.0001

Data Index: 1180788 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 6.2374. Min Range: -6.2374

Max Act: 3.0571. Min Act: -0.0000

Data Index: 999231 (C4 (Web Text))

Max Activating Token Index: 812