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

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

Neuron 1434 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2213. Min Range: -3.2213

Max Act: 3.2213. Min Act: -0.0000

Data Index: 507796 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 3.2213. Min Range: -3.2213

Max Act: 3.1245. Min Act: -0.0001

Data Index: 882918 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.8308. Min Act: -0.0000

Data Index: 1336937 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.7549. Min Act: -0.0001

Data Index: 66698 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.5623. Min Act: -0.0000

Data Index: 372799 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.5045. Min Act: -0.0001

Data Index: 936571 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.6327. Min Act: -0.0001

Data Index: 938618 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.4642. Min Act: -0.0001

Data Index: 1205638 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.0647. Min Act: -0.0001

Data Index: 1241128 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.3928. Min Act: -0.0000

Data Index: 330034 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.3787. Min Act: -0.0001

Data Index: 1207868 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.6060. Min Act: -0.0001

Data Index: 414775 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.4721. Min Act: -0.0000

Data Index: 380876 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.4264. Min Act: -0.0000

Data Index: 439886 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.0810. Min Act: -0.0000

Data Index: 389036 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.2946. Min Act: -0.0001

Data Index: 635126 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.0767. Min Act: -0.0000

Data Index: 439613 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.1893. Min Act: -0.0001

Data Index: 814085 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.3221. Min Act: -0.0001

Data Index: 835485 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.2823. Min Act: -0.0001

Data Index: 1032048 (C4 (Web Text))

Max Activating Token Index: 209