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

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

Neuron 1393 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9278. Min Range: -3.9278

Max Act: 3.6523. Min Act: -0.0000

Data Index: 738058 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 3.9278. Min Range: -3.9278

Max Act: 3.9278. Min Act: -0.0000

Data Index: 844385 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 3.9278. Min Range: -3.9278

Max Act: 3.3954. Min Act: -0.0000

Data Index: 166949 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 3.9278. Min Range: -3.9278

Max Act: 3.3937. Min Act: -0.0000

Data Index: 648848 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 3.9278. Min Range: -3.9278

Max Act: 3.2855. Min Act: -0.0000

Data Index: 549402 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 3.9278. Min Range: -3.9278

Max Act: 3.2455. Min Act: -0.0000

Data Index: 938131 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 3.9278. Min Range: -3.9278

Max Act: 3.3877. Min Act: -0.0000

Data Index: 916649 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 3.9278. Min Range: -3.9278

Max Act: 3.1630. Min Act: -0.0000

Data Index: 532720 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 3.9278. Min Range: -3.9278

Max Act: 3.1665. Min Act: -0.0000

Data Index: 692544 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 3.9278. Min Range: -3.9278

Max Act: 3.1481. Min Act: -0.0000

Data Index: 267399 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 3.9278. Min Range: -3.9278

Max Act: 3.1053. Min Act: -0.0000

Data Index: 929721 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 3.9278. Min Range: -3.9278

Max Act: 3.0196. Min Act: -0.0000

Data Index: 247024 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 3.9278. Min Range: -3.9278

Max Act: 3.0029. Min Act: -0.0000

Data Index: 1161991 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 3.9278. Min Range: -3.9278

Max Act: 3.1234. Min Act: -0.0000

Data Index: 235630 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 3.9278. Min Range: -3.9278

Max Act: 2.9434. Min Act: -0.0000

Data Index: 323143 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 3.9278. Min Range: -3.9278

Max Act: 2.7922. Min Act: -0.0000

Data Index: 975056 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 3.9278. Min Range: -3.9278

Max Act: 2.7885. Min Act: -0.0000

Data Index: 1270486 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 3.9278. Min Range: -3.9278

Max Act: 2.9181. Min Act: -0.0000

Data Index: 900569 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 3.9278. Min Range: -3.9278

Max Act: 2.9183. Min Act: -0.0000

Data Index: 21259 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 3.9278. Min Range: -3.9278

Max Act: 2.8645. Min Act: -0.0000

Data Index: 1302086 (C4 (Web Text))

Max Activating Token Index: 453