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

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

Neuron 4270 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: 0.7527. Min Range: -0.7527

Max Act: 0.7527. Min Act: -0.0000

Data Index: 571295 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.7389. Min Act: -0.0000

Data Index: 100560 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.7093. Min Act: -0.0000

Data Index: 781676 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.6678. Min Act: -0.0000

Data Index: 60838 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.6877. Min Act: -0.0000

Data Index: 414572 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.6708. Min Act: -0.0000

Data Index: 31126 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.6642. Min Act: -0.0000

Data Index: 834146 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.6690. Min Act: -0.0000

Data Index: 153064 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.6107. Min Act: -0.0000

Data Index: 241038 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.5822. Min Act: -0.0000

Data Index: 792311 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.5194. Min Act: -0.0000

Data Index: 7036 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.4873. Min Act: -0.0000

Data Index: 220967 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.5259. Min Act: -0.0000

Data Index: 490451 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.5237. Min Act: -0.0000

Data Index: 277059 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.4991. Min Act: -0.0000

Data Index: 712983 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.4983. Min Act: -0.0000

Data Index: 737526 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.4851. Min Act: -0.0000

Data Index: 283760 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.4884. Min Act: -0.0000

Data Index: 924591 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.5070. Min Act: -0.0000

Data Index: 505706 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.5802. Min Act: -0.0000

Data Index: 815198 (C4 (Web Text))

Max Activating Token Index: 196