Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 503 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.4415. Min Range: -3.4415

Max Act: 3.4415. Min Act: -0.0001

Data Index: 1264415 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 3.4415. Min Range: -3.4415

Max Act: 3.2341. Min Act: -0.0001

Data Index: 522602 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 3.4415. Min Range: -3.4415

Max Act: 3.1136. Min Act: -0.0001

Data Index: 699489 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 3.4415. Min Range: -3.4415

Max Act: 3.0042. Min Act: -0.0001

Data Index: 387387 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 3.4415. Min Range: -3.4415

Max Act: 2.6450. Min Act: -0.0001

Data Index: 805542 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 3.4415. Min Range: -3.4415

Max Act: 2.8771. Min Act: -0.0001

Data Index: 1065630 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 3.4415. Min Range: -3.4415

Max Act: 2.8169. Min Act: -0.0001

Data Index: 193851 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 3.4415. Min Range: -3.4415

Max Act: 2.6721. Min Act: -0.0001

Data Index: 1406709 (Python Code)

Max Activating Token Index: 806

Text #8

Max Range: 3.4415. Min Range: -3.4415

Max Act: 2.5592. Min Act: -0.0001

Data Index: 1361376 (Python Code)

Max Activating Token Index: 955

Text #9

Max Range: 3.4415. Min Range: -3.4415

Max Act: 2.4477. Min Act: -0.0001

Data Index: 1565132 (Python Code)

Max Activating Token Index: 459

Text #10

Max Range: 3.4415. Min Range: -3.4415

Max Act: 2.3707. Min Act: -0.0001

Data Index: 602025 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 3.4415. Min Range: -3.4415

Max Act: 2.4720. Min Act: -0.0000

Data Index: 807765 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 3.4415. Min Range: -3.4415

Max Act: 2.3783. Min Act: -0.0001

Data Index: 386412 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 3.4415. Min Range: -3.4415

Max Act: 2.4917. Min Act: -0.0001

Data Index: 534480 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 3.4415. Min Range: -3.4415

Max Act: 2.3482. Min Act: -0.0001

Data Index: 945047 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 3.4415. Min Range: -3.4415

Max Act: 2.3530. Min Act: -0.0001

Data Index: 1563276 (Python Code)

Max Activating Token Index: 571

Text #16

Max Range: 3.4415. Min Range: -3.4415

Max Act: 2.3138. Min Act: -0.0000

Data Index: 1068382 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 3.4415. Min Range: -3.4415

Max Act: 2.3053. Min Act: -0.0001

Data Index: 558883 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 3.4415. Min Range: -3.4415

Max Act: 2.1707. Min Act: -0.0001

Data Index: 261695 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 3.4415. Min Range: -3.4415

Max Act: 2.2129. Min Act: -0.0001

Data Index: 1585153 (Python Code)

Max Activating Token Index: 924