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

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

Neuron 5967 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0628. Min Range: -1.0628

Max Act: 1.0628. Min Act: -0.0000

Data Index: 840562 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.9979. Min Act: -0.0000

Data Index: 889885 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.9845. Min Act: -0.0000

Data Index: 1076061 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.9821. Min Act: -0.0000

Data Index: 652541 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.9548. Min Act: -0.0000

Data Index: 518153 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.9494. Min Act: -0.0000

Data Index: 1052316 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 1.0628. Min Range: -1.0628

Max Act: 1.0086. Min Act: -0.0000

Data Index: 511322 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.9637. Min Act: -0.0000

Data Index: 314780 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.8892. Min Act: -0.0000

Data Index: 245339 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.8647. Min Act: -0.0000

Data Index: 548611 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.8840. Min Act: -0.0000

Data Index: 1234465 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.8220. Min Act: -0.0000

Data Index: 1297829 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.8134. Min Act: -0.0000

Data Index: 1148639 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.7497. Min Act: -0.0000

Data Index: 937403 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1263370 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.7221. Min Act: -0.0000

Data Index: 630790 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.7127. Min Act: -0.0000

Data Index: 494059 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.7139. Min Act: -0.0000

Data Index: 98712 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.6618. Min Act: -0.0000

Data Index: 264297 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 1.0628. Min Range: -1.0628

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1097514 (C4 (Web Text))

Max Activating Token Index: 773