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

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

Neuron 3811 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.9176. Min Act: -0.0001

Data Index: 1447243 (Python Code)

Max Activating Token Index: 491

Text #1

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.6466. Min Act: -0.0001

Data Index: 1531859 (Python Code)

Max Activating Token Index: 86

Text #2

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.4113. Min Act: -0.0000

Data Index: 779643 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.3931. Min Act: -0.0001

Data Index: 443645 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.4696. Min Act: -0.0001

Data Index: 1322511 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.4453. Min Act: -0.0001

Data Index: 1117629 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.3226. Min Act: -0.0001

Data Index: 885820 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.3922. Min Act: -0.0000

Data Index: 356876 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.3289. Min Act: -0.0001

Data Index: 132799 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.3494. Min Act: -0.0001

Data Index: 290360 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.3448. Min Act: -0.0001

Data Index: 108944 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.3345. Min Act: -0.0001

Data Index: 1444400 (Python Code)

Max Activating Token Index: 474

Text #12

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.2805. Min Act: -0.0001

Data Index: 1247622 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.3654. Min Act: -0.0001

Data Index: 1454904 (Python Code)

Max Activating Token Index: 644

Text #14

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.3883. Min Act: -0.0001

Data Index: 61723 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.2926. Min Act: -0.0001

Data Index: 1521625 (Python Code)

Max Activating Token Index: 34

Text #16

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.2860. Min Act: -0.0001

Data Index: 1528668 (Python Code)

Max Activating Token Index: 276

Text #17

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.1640. Min Act: -0.0001

Data Index: 1441160 (Python Code)

Max Activating Token Index: 555

Text #18

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.2795. Min Act: -0.0001

Data Index: 379067 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.2293. Min Act: -0.0001

Data Index: 117413 (C4 (Web Text))

Max Activating Token Index: 196