Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1242 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.2902. Min Act: -0.0000

Data Index: 1004241 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.3373. Min Act: -0.0000

Data Index: 561546 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.1557. Min Act: -0.0000

Data Index: 616866 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.1096. Min Act: -0.0000

Data Index: 357154 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.0779. Min Act: -0.0000

Data Index: 1153181 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.0729. Min Act: -0.0000

Data Index: 432051 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.0404. Min Act: -0.0000

Data Index: 1240331 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.0341. Min Act: -0.0000

Data Index: 225961 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.3117. Min Act: -0.0000

Data Index: 809887 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.1603. Min Act: -0.0000

Data Index: 983901 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 3.3373. Min Range: -3.3373

Max Act: 2.8578. Min Act: -0.0000

Data Index: 830017 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 3.3373. Min Range: -3.3373

Max Act: 2.9865. Min Act: -0.0000

Data Index: 86843 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 3.3373. Min Range: -3.3373

Max Act: 2.8498. Min Act: -0.0000

Data Index: 1253224 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.0005. Min Act: -0.0000

Data Index: 584370 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 3.3373. Min Range: -3.3373

Max Act: 2.7810. Min Act: -0.0000

Data Index: 181106 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 3.3373. Min Range: -3.3373

Max Act: 2.7545. Min Act: -0.0000

Data Index: 137323 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 3.3373. Min Range: -3.3373

Max Act: 2.9182. Min Act: -0.0000

Data Index: 555222 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 3.3373. Min Range: -3.3373

Max Act: 2.7432. Min Act: -0.0000

Data Index: 193058 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 3.3373. Min Range: -3.3373

Max Act: 2.7064. Min Act: -0.0000

Data Index: 796826 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 3.3373. Min Range: -3.3373

Max Act: 2.7069. Min Act: -0.0000

Data Index: 600742 (C4 (Web Text))

Max Activating Token Index: 77