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

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

Neuron 2947 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1238. Min Range: -1.1238

Max Act: 1.0248. Min Act: -0.0000

Data Index: 1153696 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 1.1238. Min Range: -1.1238

Max Act: 1.0822. Min Act: -0.0000

Data Index: 663946 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 1.1238. Min Range: -1.1238

Max Act: 1.1238. Min Act: -0.0000

Data Index: 321149 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.9316. Min Act: -0.0000

Data Index: 219290 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.9830. Min Act: -0.0000

Data Index: 259358 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.9977. Min Act: -0.0000

Data Index: 811000 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.9602. Min Act: -0.0000

Data Index: 601147 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.9621. Min Act: -0.0000

Data Index: 1312153 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.9140. Min Act: -0.0000

Data Index: 1156071 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 1.1238. Min Range: -1.1238

Max Act: 1.0072. Min Act: -0.0000

Data Index: 470602 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.9195. Min Act: -0.0000

Data Index: 1221860 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.9398. Min Act: -0.0000

Data Index: 1250053 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 1.1238. Min Range: -1.1238

Max Act: 1.0244. Min Act: -0.0001

Data Index: 1307920 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.8617. Min Act: -0.0000

Data Index: 46038 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.8917. Min Act: -0.0000

Data Index: 1304269 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.8191. Min Act: -0.0000

Data Index: 347985 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1023950 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.8644. Min Act: -0.0000

Data Index: 77221 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.8537. Min Act: -0.0000

Data Index: 174637 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.8303. Min Act: -0.0000

Data Index: 895024 (C4 (Web Text))

Max Activating Token Index: 717