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

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

Neuron 2974 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0575. Min Range: -1.0575

Max Act: 1.0575. Min Act: -0.0000

Data Index: 1036448 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.8327. Min Act: -0.0000

Data Index: 260896 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.7610. Min Act: 0.0000

Data Index: 446569 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.7717. Min Act: -0.0001

Data Index: 52534 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.7015. Min Act: -0.0000

Data Index: 327899 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.7041. Min Act: -0.0000

Data Index: 731846 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.7448. Min Act: -0.0000

Data Index: 902465 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.6275. Min Act: -0.0000

Data Index: 782555 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.6535. Min Act: -0.0000

Data Index: 898504 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.6848. Min Act: -0.0000

Data Index: 560672 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.6767. Min Act: -0.0001

Data Index: 779389 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.6403. Min Act: 0.0000

Data Index: 1173137 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.5441. Min Act: -0.0000

Data Index: 1068184 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.6543. Min Act: -0.0001

Data Index: 196432 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.6199. Min Act: -0.0000

Data Index: 687311 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.5862. Min Act: 0.0000

Data Index: 610888 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.6244. Min Act: -0.0000

Data Index: 1098447 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.6456. Min Act: -0.0000

Data Index: 1093399 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1077372 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.6000. Min Act: -0.0000

Data Index: 329559 (C4 (Web Text))

Max Activating Token Index: 128