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

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

Neuron 608 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.8082. Min Act: -0.0000

Data Index: 106561 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.7351. Min Act: -0.0000

Data Index: 382802 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.6592. Min Act: -0.0000

Data Index: 440605 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1278007 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.5456. Min Act: -0.0000

Data Index: 1082219 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.5139. Min Act: -0.0000

Data Index: 296706 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1072214 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.5099. Min Act: -0.0000

Data Index: 964817 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.4801. Min Act: -0.0000

Data Index: 999835 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.4854. Min Act: -0.0000

Data Index: 656339 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.4089. Min Act: -0.0000

Data Index: 1548627 (Python Code)

Max Activating Token Index: 151

Text #11

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.4294. Min Act: -0.0000

Data Index: 1509322 (Python Code)

Max Activating Token Index: 403

Text #12

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.4409. Min Act: -0.0000

Data Index: 1586552 (Python Code)

Max Activating Token Index: 114

Text #13

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.3962. Min Act: -0.0000

Data Index: 891698 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.3650. Min Act: -0.0000

Data Index: 582028 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1640980 (Python Code)

Max Activating Token Index: 837

Text #16

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.3729. Min Act: -0.0000

Data Index: 1510642 (Python Code)

Max Activating Token Index: 259

Text #17

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1643752 (Python Code)

Max Activating Token Index: 245

Text #18

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.3628. Min Act: -0.0000

Data Index: 1581021 (Python Code)

Max Activating Token Index: 430

Text #19

Max Range: 0.8082. Min Range: -0.8082

Max Act: 0.3639. Min Act: -0.0000

Data Index: 816875 (C4 (Web Text))

Max Activating Token Index: 793