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

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

Neuron 2985 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: 3.7727. Min Range: -3.7727

Max Act: 3.7727. Min Act: -0.0000

Data Index: 251787 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 3.7727. Min Range: -3.7727

Max Act: 3.3249. Min Act: -0.0000

Data Index: 107076 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 3.7727. Min Range: -3.7727

Max Act: 3.2288. Min Act: -0.0000

Data Index: 315132 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 3.7727. Min Range: -3.7727

Max Act: 3.4796. Min Act: -0.0000

Data Index: 1073787 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 3.7727. Min Range: -3.7727

Max Act: 3.2032. Min Act: -0.0000

Data Index: 556638 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 3.7727. Min Range: -3.7727

Max Act: 3.2191. Min Act: -0.0000

Data Index: 907748 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 3.7727. Min Range: -3.7727

Max Act: 2.8667. Min Act: -0.0000

Data Index: 1010860 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 3.7727. Min Range: -3.7727

Max Act: 2.6676. Min Act: -0.0000

Data Index: 1282258 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 3.7727. Min Range: -3.7727

Max Act: 2.8129. Min Act: -0.0001

Data Index: 334537 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 3.7727. Min Range: -3.7727

Max Act: 2.8423. Min Act: -0.0000

Data Index: 354341 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 3.7727. Min Range: -3.7727

Max Act: 2.7569. Min Act: -0.0000

Data Index: 201200 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 3.7727. Min Range: -3.7727

Max Act: 2.5504. Min Act: -0.0000

Data Index: 936666 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 3.7727. Min Range: -3.7727

Max Act: 2.6373. Min Act: -0.0000

Data Index: 327066 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 3.7727. Min Range: -3.7727

Max Act: 2.4304. Min Act: -0.0000

Data Index: 475632 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 3.7727. Min Range: -3.7727

Max Act: 2.7895. Min Act: -0.0000

Data Index: 772768 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 3.7727. Min Range: -3.7727

Max Act: 2.5364. Min Act: -0.0000

Data Index: 1413181 (Python Code)

Max Activating Token Index: 764

Text #16

Max Range: 3.7727. Min Range: -3.7727

Max Act: 2.6490. Min Act: -0.0000

Data Index: 543655 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 3.7727. Min Range: -3.7727

Max Act: 2.5330. Min Act: -0.0001

Data Index: 365737 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 3.7727. Min Range: -3.7727

Max Act: 2.6475. Min Act: -0.0000

Data Index: 152138 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 3.7727. Min Range: -3.7727

Max Act: 2.6495. Min Act: -0.0000

Data Index: 206164 (C4 (Web Text))

Max Activating Token Index: 450