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

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

Neuron 4785 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: 1.0054. Min Range: -1.0054

Max Act: 1.0054. Min Act: -0.0000

Data Index: 911852 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 1.0054. Min Range: -1.0054

Max Act: 0.9177. Min Act: -0.0000

Data Index: 403055 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 1.0054. Min Range: -1.0054

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1213377 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 1.0054. Min Range: -1.0054

Max Act: 0.8525. Min Act: -0.0000

Data Index: 371455 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 1.0054. Min Range: -1.0054

Max Act: 0.8326. Min Act: -0.0000

Data Index: 848931 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 1.0054. Min Range: -1.0054

Max Act: 0.8511. Min Act: -0.0000

Data Index: 782524 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 1.0054. Min Range: -1.0054

Max Act: 0.7784. Min Act: -0.0000

Data Index: 671560 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 1.0054. Min Range: -1.0054

Max Act: 0.8030. Min Act: -0.0000

Data Index: 925257 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 1.0054. Min Range: -1.0054

Max Act: 0.8649. Min Act: -0.0000

Data Index: 553504 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 1.0054. Min Range: -1.0054

Max Act: 0.7643. Min Act: -0.0000

Data Index: 117111 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 1.0054. Min Range: -1.0054

Max Act: 0.7613. Min Act: -0.0000

Data Index: 1066697 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 1.0054. Min Range: -1.0054

Max Act: 0.7502. Min Act: -0.0000

Data Index: 650675 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 1.0054. Min Range: -1.0054

Max Act: 0.7706. Min Act: -0.0000

Data Index: 543506 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 1.0054. Min Range: -1.0054

Max Act: 0.7239. Min Act: -0.0000

Data Index: 316509 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 1.0054. Min Range: -1.0054

Max Act: 0.6878. Min Act: -0.0000

Data Index: 431621 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 1.0054. Min Range: -1.0054

Max Act: 0.7656. Min Act: -0.0000

Data Index: 362827 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 1.0054. Min Range: -1.0054

Max Act: 0.7280. Min Act: -0.0000

Data Index: 543415 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 1.0054. Min Range: -1.0054

Max Act: 0.6957. Min Act: -0.0000

Data Index: 1099786 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 1.0054. Min Range: -1.0054

Max Act: 0.6777. Min Act: -0.0000

Data Index: 851977 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 1.0054. Min Range: -1.0054

Max Act: 0.6426. Min Act: -0.0000

Data Index: 802959 (C4 (Web Text))

Max Activating Token Index: 766