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

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

Neuron 1426 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7947. Min Range: -1.7947

Max Act: 1.6784. Min Act: -0.0001

Data Index: 184661 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 1.7947. Min Range: -1.7947

Max Act: 1.7466. Min Act: -0.0001

Data Index: 1253683 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 1.7947. Min Range: -1.7947

Max Act: 1.7947. Min Act: -0.0001

Data Index: 798208 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 1.7947. Min Range: -1.7947

Max Act: 1.6935. Min Act: -0.0001

Data Index: 165583 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 1.7947. Min Range: -1.7947

Max Act: 1.7639. Min Act: -0.0001

Data Index: 877330 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 1.7947. Min Range: -1.7947

Max Act: 1.6658. Min Act: -0.0001

Data Index: 559771 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 1.7947. Min Range: -1.7947

Max Act: 1.6936. Min Act: -0.0001

Data Index: 371275 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 1.7947. Min Range: -1.7947

Max Act: 1.5325. Min Act: -0.0001

Data Index: 1133217 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 1.7947. Min Range: -1.7947

Max Act: 1.5512. Min Act: -0.0001

Data Index: 370243 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 1.7947. Min Range: -1.7947

Max Act: 1.5406. Min Act: -0.0001

Data Index: 407207 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 1.7947. Min Range: -1.7947

Max Act: 1.6308. Min Act: -0.0001

Data Index: 354123 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 1.7947. Min Range: -1.7947

Max Act: 1.5258. Min Act: -0.0001

Data Index: 394903 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 1.7947. Min Range: -1.7947

Max Act: 1.3589. Min Act: -0.0001

Data Index: 618879 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 1.7947. Min Range: -1.7947

Max Act: 1.4379. Min Act: -0.0001

Data Index: 295840 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 1.7947. Min Range: -1.7947

Max Act: 1.4046. Min Act: -0.0001

Data Index: 363876 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 1.7947. Min Range: -1.7947

Max Act: 1.4695. Min Act: -0.0001

Data Index: 1229762 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 1.7947. Min Range: -1.7947

Max Act: 1.3559. Min Act: -0.0001

Data Index: 617308 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 1.7947. Min Range: -1.7947

Max Act: 1.3260. Min Act: -0.0001

Data Index: 1128920 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 1.7947. Min Range: -1.7947

Max Act: 1.4234. Min Act: -0.0001

Data Index: 211562 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 1.7947. Min Range: -1.7947

Max Act: 1.3122. Min Act: -0.0001

Data Index: 1259803 (C4 (Web Text))

Max Activating Token Index: 111