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

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

Neuron 2532 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.8331. Min Act: -0.0000

Data Index: 1202427 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1163093 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7686. Min Act: -0.0000

Data Index: 340321 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7321. Min Act: 0.0000

Data Index: 926104 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7951. Min Act: 0.0001

Data Index: 548077 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7416. Min Act: 0.0000

Data Index: 666205 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6905. Min Act: -0.0000

Data Index: 1318662 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6642. Min Act: -0.0000

Data Index: 660053 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6268. Min Act: 0.0001

Data Index: 744159 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6509. Min Act: -0.0000

Data Index: 489507 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6397. Min Act: -0.0000

Data Index: 620207 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6770. Min Act: -0.0000

Data Index: 156937 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6349. Min Act: -0.0000

Data Index: 453624 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6913. Min Act: -0.0000

Data Index: 821796 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6352. Min Act: -0.0000

Data Index: 232351 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6388. Min Act: -0.0000

Data Index: 489859 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6156. Min Act: -0.0000

Data Index: 779934 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6152. Min Act: -0.0000

Data Index: 472416 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6487. Min Act: -0.0000

Data Index: 106488 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1047417 (C4 (Web Text))

Max Activating Token Index: 1009