Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1260 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.6182. Min Act: -0.0001

Data Index: 546992 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.7526. Min Act: -0.0002

Data Index: 725376 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.4921. Min Act: -0.0002

Data Index: 1061300 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.4575. Min Act: -0.0002

Data Index: 868201 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.5171. Min Act: -0.0002

Data Index: 375226 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.7214. Min Act: -0.0001

Data Index: 1216065 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.3732. Min Act: -0.0001

Data Index: 121571 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.5193. Min Act: -0.0002

Data Index: 563699 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.4265. Min Act: -0.0002

Data Index: 271389 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.4245. Min Act: -0.0002

Data Index: 90500 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.3386. Min Act: -0.0002

Data Index: 1075501 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.4097. Min Act: -0.0001

Data Index: 201332 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.4104. Min Act: -0.0002

Data Index: 1359840 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.4293. Min Act: -0.0002

Data Index: 753447 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.3416. Min Act: -0.0002

Data Index: 1126970 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.3228. Min Act: -0.0001

Data Index: 563987 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.4311. Min Act: -0.0001

Data Index: 517672 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.3176. Min Act: -0.0001

Data Index: 1203566 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.3183. Min Act: -0.0002

Data Index: 864653 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.3480. Min Act: -0.0001

Data Index: 267374 (C4 (Web Text))

Max Activating Token Index: 918