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

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

Neuron 4452 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3862. Min Range: -3.3862

Max Act: 3.3862. Min Act: -0.0001

Data Index: 413427 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 3.3862. Min Range: -3.3862

Max Act: 3.1553. Min Act: -0.0001

Data Index: 149691 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 3.3862. Min Range: -3.3862

Max Act: 3.3120. Min Act: -0.0001

Data Index: 117606 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 3.3862. Min Range: -3.3862

Max Act: 2.6890. Min Act: -0.0001

Data Index: 166506 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 3.3862. Min Range: -3.3862

Max Act: 3.1418. Min Act: -0.0001

Data Index: 1129677 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 3.3862. Min Range: -3.3862

Max Act: 2.7656. Min Act: -0.0001

Data Index: 617572 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 3.3862. Min Range: -3.3862

Max Act: 3.0234. Min Act: -0.0001

Data Index: 790026 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 3.3862. Min Range: -3.3862

Max Act: 2.8025. Min Act: -0.0001

Data Index: 1309720 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 3.3862. Min Range: -3.3862

Max Act: 2.6971. Min Act: -0.0001

Data Index: 161658 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 3.3862. Min Range: -3.3862

Max Act: 2.9197. Min Act: -0.0001

Data Index: 402789 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 3.3862. Min Range: -3.3862

Max Act: 2.2550. Min Act: -0.0001

Data Index: 198060 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 3.3862. Min Range: -3.3862

Max Act: 2.2986. Min Act: -0.0001

Data Index: 850463 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 3.3862. Min Range: -3.3862

Max Act: 2.3732. Min Act: -0.0001

Data Index: 1062034 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 3.3862. Min Range: -3.3862

Max Act: 2.3769. Min Act: -0.0001

Data Index: 739566 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 3.3862. Min Range: -3.3862

Max Act: 2.3851. Min Act: -0.0001

Data Index: 1118766 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 3.3862. Min Range: -3.3862

Max Act: 2.4879. Min Act: -0.0001

Data Index: 1143103 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 3.3862. Min Range: -3.3862

Max Act: 2.1361. Min Act: -0.0001

Data Index: 72955 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 3.3862. Min Range: -3.3862

Max Act: 2.6077. Min Act: -0.0001

Data Index: 1055387 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 3.3862. Min Range: -3.3862

Max Act: 2.4943. Min Act: -0.0001

Data Index: 643509 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 3.3862. Min Range: -3.3862

Max Act: 2.5163. Min Act: -0.0001

Data Index: 14554 (C4 (Web Text))

Max Activating Token Index: 113