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

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

Neuron 4433 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: 3.1770. Min Range: -3.1770

Max Act: 3.1770. Min Act: -0.0000

Data Index: 809665 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.7867. Min Act: -0.0000

Data Index: 260231 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.7270. Min Act: -0.0000

Data Index: 239080 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.9448. Min Act: -0.0000

Data Index: 685611 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.7918. Min Act: -0.0000

Data Index: 190862 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.7219. Min Act: -0.0000

Data Index: 401526 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.8004. Min Act: -0.0000

Data Index: 943555 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.6234. Min Act: -0.0000

Data Index: 39884 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.6678. Min Act: -0.0001

Data Index: 97651 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.5443. Min Act: -0.0000

Data Index: 1337706 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.0818. Min Act: -0.0000

Data Index: 1300639 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.4895. Min Act: -0.0000

Data Index: 819774 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.6107. Min Act: -0.0000

Data Index: 47193 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.4683. Min Act: -0.0000

Data Index: 1127823 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.4459. Min Act: -0.0000

Data Index: 595169 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.4762. Min Act: -0.0000

Data Index: 396843 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.5570. Min Act: -0.0000

Data Index: 174228 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.4181. Min Act: -0.0000

Data Index: 997530 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.4314. Min Act: -0.0000

Data Index: 230963 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.4399. Min Act: -0.0000

Data Index: 494065 (C4 (Web Text))

Max Activating Token Index: 555