Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 389 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.5130. Min Act: -0.0001

Data Index: 1348515 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4865. Min Act: -0.0001

Data Index: 992023 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4311. Min Act: -0.0001

Data Index: 168482 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4369. Min Act: -0.0001

Data Index: 1132197 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4287. Min Act: -0.0001

Data Index: 127169 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4357. Min Act: -0.0001

Data Index: 1225597 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4116. Min Act: -0.0001

Data Index: 298568 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4459. Min Act: -0.0001

Data Index: 626329 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4272. Min Act: -0.0001

Data Index: 936476 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4390. Min Act: -0.0001

Data Index: 28733 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.3451. Min Act: -0.0001

Data Index: 706600 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4006. Min Act: -0.0001

Data Index: 1025755 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4157. Min Act: -0.0001

Data Index: 1098257 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4127. Min Act: -0.0001

Data Index: 1257996 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4167. Min Act: -0.0001

Data Index: 933371 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.3619. Min Act: -0.0001

Data Index: 325192 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4004. Min Act: -0.0001

Data Index: 787919 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4054. Min Act: -0.0001

Data Index: 409200 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.3586. Min Act: -0.0001

Data Index: 1199259 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4551. Min Act: -0.0001

Data Index: 765835 (C4 (Web Text))

Max Activating Token Index: 464