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

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

Neuron 2404 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8833. Min Range: -1.8833

Max Act: 1.8833. Min Act: -0.0000

Data Index: 1087373 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 1.8833. Min Range: -1.8833

Max Act: 1.4426. Min Act: -0.0000

Data Index: 829142 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 1.8833. Min Range: -1.8833

Max Act: 1.4192. Min Act: -0.0000

Data Index: 1337935 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 1.8833. Min Range: -1.8833

Max Act: 1.3242. Min Act: -0.0000

Data Index: 1173320 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 1.8833. Min Range: -1.8833

Max Act: 1.2965. Min Act: -0.0000

Data Index: 1202465 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 1.8833. Min Range: -1.8833

Max Act: 1.2305. Min Act: -0.0000

Data Index: 29110 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 1.8833. Min Range: -1.8833

Max Act: 1.3647. Min Act: -0.0000

Data Index: 511379 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 1.8833. Min Range: -1.8833

Max Act: 1.3508. Min Act: -0.0000

Data Index: 126532 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 1.8833. Min Range: -1.8833

Max Act: 1.3543. Min Act: -0.0000

Data Index: 377007 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 1.8833. Min Range: -1.8833

Max Act: 1.2170. Min Act: -0.0000

Data Index: 844775 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 1.8833. Min Range: -1.8833

Max Act: 1.2731. Min Act: -0.0000

Data Index: 1308900 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 1.8833. Min Range: -1.8833

Max Act: 1.3013. Min Act: -0.0000

Data Index: 228298 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 1.8833. Min Range: -1.8833

Max Act: 1.2344. Min Act: -0.0000

Data Index: 532006 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 1.8833. Min Range: -1.8833

Max Act: 1.1945. Min Act: -0.0000

Data Index: 730955 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 1.8833. Min Range: -1.8833

Max Act: 1.2282. Min Act: -0.0000

Data Index: 183267 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 1.8833. Min Range: -1.8833

Max Act: 1.2186. Min Act: -0.0000

Data Index: 175367 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 1.8833. Min Range: -1.8833

Max Act: 1.2463. Min Act: -0.0000

Data Index: 1214089 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 1.8833. Min Range: -1.8833

Max Act: 1.1448. Min Act: -0.0000

Data Index: 617632 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 1.8833. Min Range: -1.8833

Max Act: 1.1711. Min Act: -0.0000

Data Index: 1327933 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 1.8833. Min Range: -1.8833

Max Act: 1.1805. Min Act: -0.0000

Data Index: 752450 (C4 (Web Text))

Max Activating Token Index: 993