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

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

Neuron 4341 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.6178. Min Act: -0.0001

Data Index: 539535 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.4498. Min Act: -0.0000

Data Index: 860231 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.4159. Min Act: -0.0001

Data Index: 98682 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.3478. Min Act: -0.0000

Data Index: 38086 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.3279. Min Act: -0.0000

Data Index: 66824 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.2784. Min Act: -0.0001

Data Index: 146362 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.2376. Min Act: -0.0000

Data Index: 1103024 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.2440. Min Act: -0.0000

Data Index: 362541 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.0131. Min Act: -0.0000

Data Index: 696524 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.1631. Min Act: -0.0001

Data Index: 1516834 (Python Code)

Max Activating Token Index: 206

Text #10

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.1436. Min Act: -0.0000

Data Index: 854233 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.1173. Min Act: -0.0000

Data Index: 574482 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.1167. Min Act: -0.0000

Data Index: 1263786 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.0744. Min Act: -0.0001

Data Index: 280518 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.0623. Min Act: -0.0001

Data Index: 592879 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 3.6178. Min Range: -3.6178

Max Act: 2.8525. Min Act: -0.0000

Data Index: 1210893 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.0239. Min Act: -0.0000

Data Index: 991747 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 3.6178. Min Range: -3.6178

Max Act: 3.1310. Min Act: -0.0001

Data Index: 1626103 (Python Code)

Max Activating Token Index: 731

Text #18

Max Range: 3.6178. Min Range: -3.6178

Max Act: 2.8754. Min Act: -0.0001

Data Index: 655587 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 3.6178. Min Range: -3.6178

Max Act: 2.9822. Min Act: -0.0001

Data Index: 271562 (C4 (Web Text))

Max Activating Token Index: 507