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

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

Neuron 2325 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: 4.3616. Min Range: -4.3616

Max Act: 4.3616. Min Act: -0.0000

Data Index: 340684 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 4.3616. Min Range: -4.3616

Max Act: 4.0121. Min Act: -0.0000

Data Index: 462047 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 4.3616. Min Range: -4.3616

Max Act: 3.9742. Min Act: -0.0000

Data Index: 1342635 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 4.3616. Min Range: -4.3616

Max Act: 3.7385. Min Act: -0.0000

Data Index: 911476 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 4.3616. Min Range: -4.3616

Max Act: 3.7218. Min Act: -0.0000

Data Index: 478766 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 4.3616. Min Range: -4.3616

Max Act: 3.3266. Min Act: -0.0000

Data Index: 92376 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 4.3616. Min Range: -4.3616

Max Act: 3.6136. Min Act: -0.0000

Data Index: 387437 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 4.3616. Min Range: -4.3616

Max Act: 3.7419. Min Act: -0.0000

Data Index: 89314 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 4.3616. Min Range: -4.3616

Max Act: 3.5422. Min Act: -0.0000

Data Index: 1115552 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 4.3616. Min Range: -4.3616

Max Act: 3.4339. Min Act: -0.0000

Data Index: 126308 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 4.3616. Min Range: -4.3616

Max Act: 3.2223. Min Act: -0.0000

Data Index: 461421 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 4.3616. Min Range: -4.3616

Max Act: 3.3163. Min Act: -0.0000

Data Index: 1347724 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 4.3616. Min Range: -4.3616

Max Act: 3.4767. Min Act: -0.0000

Data Index: 390826 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 4.3616. Min Range: -4.3616

Max Act: 3.2886. Min Act: -0.0000

Data Index: 78659 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 4.3616. Min Range: -4.3616

Max Act: 3.2865. Min Act: -0.0000

Data Index: 514007 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 4.3616. Min Range: -4.3616

Max Act: 3.0901. Min Act: -0.0000

Data Index: 914079 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 4.3616. Min Range: -4.3616

Max Act: 3.1919. Min Act: -0.0000

Data Index: 1344368 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 4.3616. Min Range: -4.3616

Max Act: 3.1662. Min Act: -0.0000

Data Index: 92915 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 4.3616. Min Range: -4.3616

Max Act: 3.1449. Min Act: -0.0000

Data Index: 519330 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 4.3616. Min Range: -4.3616

Max Act: 3.0899. Min Act: -0.0000

Data Index: 792924 (C4 (Web Text))

Max Activating Token Index: 375