Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3453 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0171. Min Range: -3.0171

Max Act: 3.0171. Min Act: -0.0000

Data Index: 1196511 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.7310. Min Act: -0.0000

Data Index: 587165 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.5945. Min Act: -0.0000

Data Index: 954550 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.3821. Min Act: -0.0000

Data Index: 1070292 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.2300. Min Act: -0.0000

Data Index: 1060033 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.2079. Min Act: -0.0000

Data Index: 457267 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.1400. Min Act: -0.0000

Data Index: 1024909 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.2587. Min Act: -0.0000

Data Index: 419215 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.1205. Min Act: -0.0000

Data Index: 676272 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 3.0171. Min Range: -3.0171

Max Act: 2.1601. Min Act: -0.0000

Data Index: 1293212 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 3.0171. Min Range: -3.0171

Max Act: 1.9207. Min Act: -0.0000

Data Index: 918228 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 3.0171. Min Range: -3.0171

Max Act: 1.8490. Min Act: -0.0000

Data Index: 939648 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 3.0171. Min Range: -3.0171

Max Act: 1.9530. Min Act: -0.0000

Data Index: 790603 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 3.0171. Min Range: -3.0171

Max Act: 1.9455. Min Act: -0.0000

Data Index: 269720 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 3.0171. Min Range: -3.0171

Max Act: 1.9442. Min Act: -0.0000

Data Index: 1229831 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 3.0171. Min Range: -3.0171

Max Act: 1.8278. Min Act: -0.0000

Data Index: 503514 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 3.0171. Min Range: -3.0171

Max Act: 1.9911. Min Act: -0.0000

Data Index: 516536 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 3.0171. Min Range: -3.0171

Max Act: 1.9347. Min Act: -0.0000

Data Index: 1153591 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 3.0171. Min Range: -3.0171

Max Act: 1.8154. Min Act: -0.0000

Data Index: 744189 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 3.0171. Min Range: -3.0171

Max Act: 1.7619. Min Act: -0.0000

Data Index: 34952 (C4 (Web Text))

Max Activating Token Index: 494