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

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

Neuron 321 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7329. Min Range: -0.7329

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1295754 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.7329. Min Range: -0.7329

Max Act: 0.7329. Min Act: -0.0000

Data Index: 113826 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 0.7329. Min Range: -0.7329

Max Act: 0.6859. Min Act: -0.0000

Data Index: 561018 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.7329. Min Range: -0.7329

Max Act: 0.7067. Min Act: -0.0000

Data Index: 962370 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.7329. Min Range: -0.7329

Max Act: 0.6798. Min Act: -0.0000

Data Index: 485316 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.7329. Min Range: -0.7329

Max Act: 0.6421. Min Act: -0.0000

Data Index: 279562 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.7329. Min Range: -0.7329

Max Act: 0.6486. Min Act: -0.0000

Data Index: 3923 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 0.7329. Min Range: -0.7329

Max Act: 0.6472. Min Act: -0.0000

Data Index: 606395 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.7329. Min Range: -0.7329

Max Act: 0.6290. Min Act: -0.0000

Data Index: 228238 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.7329. Min Range: -0.7329

Max Act: 0.5937. Min Act: -0.0000

Data Index: 502484 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 0.7329. Min Range: -0.7329

Max Act: 0.5852. Min Act: -0.0000

Data Index: 8740 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 0.7329. Min Range: -0.7329

Max Act: 0.5431. Min Act: -0.0000

Data Index: 1240153 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.7329. Min Range: -0.7329

Max Act: 0.5616. Min Act: -0.0000

Data Index: 971003 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 0.7329. Min Range: -0.7329

Max Act: 0.5702. Min Act: -0.0000

Data Index: 591520 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.7329. Min Range: -0.7329

Max Act: 0.5884. Min Act: -0.0000

Data Index: 14554 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.7329. Min Range: -0.7329

Max Act: 0.5297. Min Act: -0.0000

Data Index: 60038 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 0.7329. Min Range: -0.7329

Max Act: 0.5655. Min Act: -0.0000

Data Index: 397247 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.7329. Min Range: -0.7329

Max Act: 0.5852. Min Act: -0.0000

Data Index: 462131 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.7329. Min Range: -0.7329

Max Act: 0.5362. Min Act: -0.0000

Data Index: 819468 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.7329. Min Range: -0.7329

Max Act: 0.5293. Min Act: -0.0000

Data Index: 469058 (C4 (Web Text))

Max Activating Token Index: 446