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

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

Neuron 3142 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1318. Min Range: -5.1318

Max Act: 5.1318. Min Act: -0.0000

Data Index: 1312416 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 5.1318. Min Range: -5.1318

Max Act: 3.8103. Min Act: -0.0000

Data Index: 1071810 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 5.1318. Min Range: -5.1318

Max Act: 3.7406. Min Act: -0.0000

Data Index: 1113561 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 5.1318. Min Range: -5.1318

Max Act: 3.6215. Min Act: 0.0000

Data Index: 1319940 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 5.1318. Min Range: -5.1318

Max Act: 3.6176. Min Act: -0.0000

Data Index: 381666 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 5.1318. Min Range: -5.1318

Max Act: 3.3298. Min Act: -0.0000

Data Index: 1306362 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 5.1318. Min Range: -5.1318

Max Act: 3.3112. Min Act: -0.0000

Data Index: 649399 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 5.1318. Min Range: -5.1318

Max Act: 3.2738. Min Act: -0.0000

Data Index: 1280076 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 5.1318. Min Range: -5.1318

Max Act: 3.3492. Min Act: -0.0000

Data Index: 346933 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 5.1318. Min Range: -5.1318

Max Act: 3.1896. Min Act: -0.0000

Data Index: 126599 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 5.1318. Min Range: -5.1318

Max Act: 3.1944. Min Act: -0.0000

Data Index: 312546 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 5.1318. Min Range: -5.1318

Max Act: 3.0589. Min Act: -0.0000

Data Index: 71358 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 5.1318. Min Range: -5.1318

Max Act: 2.9902. Min Act: -0.0000

Data Index: 382149 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 5.1318. Min Range: -5.1318

Max Act: 2.9752. Min Act: -0.0000

Data Index: 813461 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 5.1318. Min Range: -5.1318

Max Act: 2.9528. Min Act: -0.0000

Data Index: 405162 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 5.1318. Min Range: -5.1318

Max Act: 3.1089. Min Act: -0.0000

Data Index: 428480 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 5.1318. Min Range: -5.1318

Max Act: 2.9298. Min Act: -0.0000

Data Index: 758078 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 5.1318. Min Range: -5.1318

Max Act: 3.0347. Min Act: -0.0000

Data Index: 1142787 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 5.1318. Min Range: -5.1318

Max Act: 2.9480. Min Act: -0.0000

Data Index: 870023 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 5.1318. Min Range: -5.1318

Max Act: 3.1022. Min Act: -0.0000

Data Index: 108974 (C4 (Web Text))

Max Activating Token Index: 141