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

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

Neuron 3268 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5924. Min Act: -0.0000

Data Index: 313547 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5807. Min Act: -0.0000

Data Index: 1072883 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5339. Min Act: -0.0000

Data Index: 670097 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5092. Min Act: -0.0000

Data Index: 499530 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4852. Min Act: -0.0000

Data Index: 1138589 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4818. Min Act: -0.0000

Data Index: 779518 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4646. Min Act: -0.0000

Data Index: 88249 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4608. Min Act: -0.0000

Data Index: 634600 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4408. Min Act: -0.0000

Data Index: 619781 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4479. Min Act: -0.0000

Data Index: 946159 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4059. Min Act: -0.0000

Data Index: 44719 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1061756 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1051624 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.3717. Min Act: -0.0000

Data Index: 434120 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.3960. Min Act: -0.0000

Data Index: 649265 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.3649. Min Act: -0.0000

Data Index: 150053 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4158. Min Act: -0.0000

Data Index: 715942 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.3862. Min Act: -0.0000

Data Index: 1340887 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.3945. Min Act: -0.0000

Data Index: 452061 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.3456. Min Act: -0.0000

Data Index: 1296997 (C4 (Web Text))

Max Activating Token Index: 1000