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

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

Neuron 3478 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: 5.4937. Min Range: -5.4937

Max Act: 5.4937. Min Act: -0.0000

Data Index: 1111384 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 5.4937. Min Range: -5.4937

Max Act: 4.6241. Min Act: -0.0000

Data Index: 932422 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 5.4937. Min Range: -5.4937

Max Act: 4.7628. Min Act: -0.0000

Data Index: 727192 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 5.4937. Min Range: -5.4937

Max Act: 4.3814. Min Act: -0.0000

Data Index: 655099 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 5.4937. Min Range: -5.4937

Max Act: 3.9807. Min Act: -0.0000

Data Index: 781623 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 5.4937. Min Range: -5.4937

Max Act: 3.8444. Min Act: -0.0000

Data Index: 202568 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 5.4937. Min Range: -5.4937

Max Act: 3.7851. Min Act: -0.0000

Data Index: 793626 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 5.4937. Min Range: -5.4937

Max Act: 3.8085. Min Act: -0.0000

Data Index: 923894 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 5.4937. Min Range: -5.4937

Max Act: 3.5538. Min Act: -0.0000

Data Index: 1180426 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 5.4937. Min Range: -5.4937

Max Act: 3.3873. Min Act: -0.0000

Data Index: 949551 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 5.4937. Min Range: -5.4937

Max Act: 3.4363. Min Act: -0.0000

Data Index: 646082 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 5.4937. Min Range: -5.4937

Max Act: 3.0967. Min Act: -0.0000

Data Index: 1000296 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 5.4937. Min Range: -5.4937

Max Act: 3.0399. Min Act: -0.0000

Data Index: 803478 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 5.4937. Min Range: -5.4937

Max Act: 3.4525. Min Act: -0.0000

Data Index: 314497 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 5.4937. Min Range: -5.4937

Max Act: 3.3357. Min Act: -0.0000

Data Index: 521045 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 5.4937. Min Range: -5.4937

Max Act: 2.7892. Min Act: -0.0000

Data Index: 549497 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 5.4937. Min Range: -5.4937

Max Act: 2.3219. Min Act: -0.0000

Data Index: 541398 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 5.4937. Min Range: -5.4937

Max Act: 2.0797. Min Act: -0.0000

Data Index: 513426 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 5.4937. Min Range: -5.4937

Max Act: 1.9890. Min Act: -0.0000

Data Index: 56331 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 5.4937. Min Range: -5.4937

Max Act: 2.0410. Min Act: -0.0000

Data Index: 1346309 (C4 (Web Text))

Max Activating Token Index: 288