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

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

Neuron 5053 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3322. Min Range: -2.3322

Max Act: 2.3322. Min Act: -0.0000

Data Index: 752694 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 2.3322. Min Range: -2.3322

Max Act: 2.2103. Min Act: -0.0000

Data Index: 83789 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 2.3322. Min Range: -2.3322

Max Act: 2.1660. Min Act: -0.0000

Data Index: 833881 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 2.3322. Min Range: -2.3322

Max Act: 2.1463. Min Act: -0.0000

Data Index: 1280366 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 2.3322. Min Range: -2.3322

Max Act: 2.1206. Min Act: -0.0000

Data Index: 976331 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 2.3322. Min Range: -2.3322

Max Act: 1.9665. Min Act: -0.0000

Data Index: 227110 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 2.3322. Min Range: -2.3322

Max Act: 2.0271. Min Act: -0.0000

Data Index: 244885 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 2.3322. Min Range: -2.3322

Max Act: 1.8936. Min Act: -0.0000

Data Index: 1339477 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 2.3322. Min Range: -2.3322

Max Act: 1.9784. Min Act: -0.0000

Data Index: 920224 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 2.3322. Min Range: -2.3322

Max Act: 1.9477. Min Act: -0.0000

Data Index: 984612 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 2.3322. Min Range: -2.3322

Max Act: 1.8684. Min Act: -0.0000

Data Index: 952270 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 2.3322. Min Range: -2.3322

Max Act: 1.8332. Min Act: -0.0000

Data Index: 675674 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 2.3322. Min Range: -2.3322

Max Act: 1.9334. Min Act: -0.0000

Data Index: 109173 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 2.3322. Min Range: -2.3322

Max Act: 1.7331. Min Act: -0.0000

Data Index: 776350 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 2.3322. Min Range: -2.3322

Max Act: 1.8403. Min Act: -0.0000

Data Index: 958472 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 2.3322. Min Range: -2.3322

Max Act: 1.7389. Min Act: -0.0000

Data Index: 25670 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 2.3322. Min Range: -2.3322

Max Act: 1.8248. Min Act: -0.0000

Data Index: 276721 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 2.3322. Min Range: -2.3322

Max Act: 1.7267. Min Act: -0.0000

Data Index: 725322 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 2.3322. Min Range: -2.3322

Max Act: 1.8139. Min Act: -0.0000

Data Index: 1131325 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 2.3322. Min Range: -2.3322

Max Act: 1.6266. Min Act: -0.0000

Data Index: 1026925 (C4 (Web Text))

Max Activating Token Index: 711