Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 195 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.4342. Min Act: -0.0001

Data Index: 1268910 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.4340. Min Act: -0.0001

Data Index: 37626 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3854. Min Act: -0.0001

Data Index: 487352 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3842. Min Act: -0.0001

Data Index: 193520 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3873. Min Act: -0.0001

Data Index: 1134177 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3893. Min Act: -0.0001

Data Index: 759961 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3682. Min Act: -0.0001

Data Index: 334301 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3329. Min Act: -0.0001

Data Index: 1055993 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3589. Min Act: -0.0001

Data Index: 195383 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3958. Min Act: -0.0001

Data Index: 706137 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3808. Min Act: -0.0001

Data Index: 86334 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3668. Min Act: -0.0001

Data Index: 647692 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3491. Min Act: -0.0001

Data Index: 694923 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3588. Min Act: -0.0001

Data Index: 829752 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3677. Min Act: -0.0001

Data Index: 1092061 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3207. Min Act: -0.0001

Data Index: 1185044 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3503. Min Act: -0.0001

Data Index: 1102996 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3379. Min Act: -0.0001

Data Index: 1114413 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3498. Min Act: -0.0001

Data Index: 255079 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3340. Min Act: -0.0001

Data Index: 615969 (C4 (Web Text))

Max Activating Token Index: 528