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

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

Neuron 82 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0612. Min Act: -0.0002

Data Index: 407914 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0606. Min Act: -0.0002

Data Index: 572483 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0636. Min Act: -0.0002

Data Index: 22455 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0593. Min Act: -0.0002

Data Index: 687245 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0587. Min Act: -0.0002

Data Index: 360835 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0592. Min Act: -0.0002

Data Index: 985003 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0567. Min Act: -0.0002

Data Index: 5701 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0549. Min Act: -0.0002

Data Index: 958588 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0514. Min Act: -0.0002

Data Index: 898936 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0547. Min Act: -0.0002

Data Index: 854170 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1184397 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0510. Min Act: -0.0002

Data Index: 671996 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0509. Min Act: -0.0002

Data Index: 644184 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0471. Min Act: -0.0002

Data Index: 597494 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0526. Min Act: -0.0002

Data Index: 638141 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1235843 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0501. Min Act: -0.0002

Data Index: 283039 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0480. Min Act: -0.0002

Data Index: 97230 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0515. Min Act: -0.0002

Data Index: 955441 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0480. Min Act: -0.0002

Data Index: 421228 (C4 (Web Text))

Max Activating Token Index: 513