Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4769 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.1304. Min Range: -4.1304

Max Act: 4.1304. Min Act: -0.0000

Data Index: 316098 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 4.1304. Min Range: -4.1304

Max Act: 3.2515. Min Act: -0.0001

Data Index: 97310 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 4.1304. Min Range: -4.1304

Max Act: 2.9829. Min Act: -0.0000

Data Index: 122506 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 4.1304. Min Range: -4.1304

Max Act: 2.6900. Min Act: -0.0001

Data Index: 1182174 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 4.1304. Min Range: -4.1304

Max Act: 2.8451. Min Act: -0.0001

Data Index: 468133 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 4.1304. Min Range: -4.1304

Max Act: 2.7720. Min Act: -0.0000

Data Index: 818727 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 4.1304. Min Range: -4.1304

Max Act: 2.5927. Min Act: -0.0000

Data Index: 1319178 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 4.1304. Min Range: -4.1304

Max Act: 2.8137. Min Act: -0.0000

Data Index: 1350931 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 4.1304. Min Range: -4.1304

Max Act: 2.6628. Min Act: -0.0000

Data Index: 998398 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 4.1304. Min Range: -4.1304

Max Act: 2.7734. Min Act: -0.0000

Data Index: 1176512 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 4.1304. Min Range: -4.1304

Max Act: 2.7578. Min Act: -0.0000

Data Index: 147317 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 4.1304. Min Range: -4.1304

Max Act: 2.4598. Min Act: -0.0000

Data Index: 215545 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 4.1304. Min Range: -4.1304

Max Act: 2.7249. Min Act: -0.0000

Data Index: 988427 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 4.1304. Min Range: -4.1304

Max Act: 2.5960. Min Act: -0.0000

Data Index: 200340 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 4.1304. Min Range: -4.1304

Max Act: 2.5791. Min Act: -0.0000

Data Index: 1012484 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 4.1304. Min Range: -4.1304

Max Act: 2.5484. Min Act: -0.0000

Data Index: 437002 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 4.1304. Min Range: -4.1304

Max Act: 2.5515. Min Act: -0.0000

Data Index: 442409 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 4.1304. Min Range: -4.1304

Max Act: 2.5522. Min Act: -0.0000

Data Index: 273097 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 4.1304. Min Range: -4.1304

Max Act: 2.4255. Min Act: -0.0000

Data Index: 811531 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 4.1304. Min Range: -4.1304

Max Act: 2.4816. Min Act: -0.0000

Data Index: 428789 (C4 (Web Text))

Max Activating Token Index: 63