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

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

Neuron 4757 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0672. Min Range: -6.0672

Max Act: 5.9191. Min Act: -0.0000

Data Index: 1075392 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 6.0672. Min Range: -6.0672

Max Act: 6.0672. Min Act: -0.0000

Data Index: 590151 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 6.0672. Min Range: -6.0672

Max Act: 5.7987. Min Act: -0.0000

Data Index: 1307157 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 6.0672. Min Range: -6.0672

Max Act: 5.4330. Min Act: -0.0000

Data Index: 1142879 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 6.0672. Min Range: -6.0672

Max Act: 5.3680. Min Act: -0.0000

Data Index: 1008191 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 6.0672. Min Range: -6.0672

Max Act: 5.3306. Min Act: -0.0000

Data Index: 1070441 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 6.0672. Min Range: -6.0672

Max Act: 5.1730. Min Act: -0.0000

Data Index: 1124739 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 6.0672. Min Range: -6.0672

Max Act: 4.9528. Min Act: -0.0000

Data Index: 1052275 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 6.0672. Min Range: -6.0672

Max Act: 4.7553. Min Act: -0.0000

Data Index: 1149620 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 6.0672. Min Range: -6.0672

Max Act: 5.0928. Min Act: -0.0000

Data Index: 1265475 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 6.0672. Min Range: -6.0672

Max Act: 4.6518. Min Act: -0.0000

Data Index: 818169 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 6.0672. Min Range: -6.0672

Max Act: 5.0488. Min Act: -0.0000

Data Index: 1243898 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 6.0672. Min Range: -6.0672

Max Act: 4.5902. Min Act: -0.0000

Data Index: 940314 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 6.0672. Min Range: -6.0672

Max Act: 4.7258. Min Act: -0.0000

Data Index: 1043518 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 6.0672. Min Range: -6.0672

Max Act: 4.5166. Min Act: -0.0000

Data Index: 514056 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 6.0672. Min Range: -6.0672

Max Act: 4.4323. Min Act: -0.0000

Data Index: 813655 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 6.0672. Min Range: -6.0672

Max Act: 4.6049. Min Act: -0.0000

Data Index: 988447 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 6.0672. Min Range: -6.0672

Max Act: 4.3914. Min Act: -0.0000

Data Index: 244723 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 6.0672. Min Range: -6.0672

Max Act: 4.3976. Min Act: -0.0000

Data Index: 877407 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 6.0672. Min Range: -6.0672

Max Act: 4.1946. Min Act: -0.0000

Data Index: 1080890 (C4 (Web Text))

Max Activating Token Index: 779