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

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

Neuron 3021 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: 4.2038. Min Range: -4.2038

Max Act: 4.2038. Min Act: -0.0000

Data Index: 1058652 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 4.2038. Min Range: -4.2038

Max Act: 3.7317. Min Act: -0.0000

Data Index: 1289048 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 4.2038. Min Range: -4.2038

Max Act: 2.9572. Min Act: -0.0000

Data Index: 563302 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 4.2038. Min Range: -4.2038

Max Act: 3.0397. Min Act: -0.0000

Data Index: 1448806 (Python Code)

Max Activating Token Index: 176

Text #4

Max Range: 4.2038. Min Range: -4.2038

Max Act: 2.8077. Min Act: -0.0000

Data Index: 972505 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 4.2038. Min Range: -4.2038

Max Act: 2.8556. Min Act: -0.0000

Data Index: 686001 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 4.2038. Min Range: -4.2038

Max Act: 2.9592. Min Act: -0.0000

Data Index: 1469576 (Python Code)

Max Activating Token Index: 288

Text #7

Max Range: 4.2038. Min Range: -4.2038

Max Act: 2.9119. Min Act: -0.0000

Data Index: 1508285 (Python Code)

Max Activating Token Index: 200

Text #8

Max Range: 4.2038. Min Range: -4.2038

Max Act: 2.7234. Min Act: -0.0000

Data Index: 1141236 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 4.2038. Min Range: -4.2038

Max Act: 2.8069. Min Act: -0.0000

Data Index: 1606866 (Python Code)

Max Activating Token Index: 787

Text #10

Max Range: 4.2038. Min Range: -4.2038

Max Act: 2.6973. Min Act: -0.0000

Data Index: 629063 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 4.2038. Min Range: -4.2038

Max Act: 2.6273. Min Act: -0.0000

Data Index: 1205919 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 4.2038. Min Range: -4.2038

Max Act: 2.8903. Min Act: -0.0000

Data Index: 588938 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 4.2038. Min Range: -4.2038

Max Act: 2.2250. Min Act: -0.0000

Data Index: 1464384 (Python Code)

Max Activating Token Index: 413

Text #14

Max Range: 4.2038. Min Range: -4.2038

Max Act: 2.3421. Min Act: -0.0000

Data Index: 1378919 (Python Code)

Max Activating Token Index: 828

Text #15

Max Range: 4.2038. Min Range: -4.2038

Max Act: 2.3930. Min Act: -0.0000

Data Index: 1114974 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 4.2038. Min Range: -4.2038

Max Act: 2.3697. Min Act: -0.0000

Data Index: 158025 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 4.2038. Min Range: -4.2038

Max Act: 2.4911. Min Act: -0.0000

Data Index: 1488917 (Python Code)

Max Activating Token Index: 593

Text #18

Max Range: 4.2038. Min Range: -4.2038

Max Act: 2.3583. Min Act: -0.0000

Data Index: 1328796 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 4.2038. Min Range: -4.2038

Max Act: 2.3292. Min Act: -0.0000

Data Index: 1654353 (Python Code)

Max Activating Token Index: 681