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

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

Neuron 2800 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2784. Min Range: -1.2784

Max Act: 1.2784. Min Act: -0.0000

Data Index: 1295538 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 1.2784. Min Range: -1.2784

Max Act: 1.2332. Min Act: -0.0000

Data Index: 992613 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 1.2784. Min Range: -1.2784

Max Act: 1.1225. Min Act: -0.0000

Data Index: 903478 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 1.2784. Min Range: -1.2784

Max Act: 1.0228. Min Act: -0.0000

Data Index: 153518 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 1.2784. Min Range: -1.2784

Max Act: 1.0591. Min Act: -0.0000

Data Index: 1127915 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 1.2784. Min Range: -1.2784

Max Act: 1.0881. Min Act: -0.0000

Data Index: 696991 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 1.2784. Min Range: -1.2784

Max Act: 1.0482. Min Act: -0.0000

Data Index: 406342 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 1.2784. Min Range: -1.2784

Max Act: 1.0051. Min Act: -0.0000

Data Index: 292873 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 1.2784. Min Range: -1.2784

Max Act: 1.0332. Min Act: -0.0000

Data Index: 1202400 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 1.2784. Min Range: -1.2784

Max Act: 1.0239. Min Act: -0.0000

Data Index: 293227 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.9887. Min Act: -0.0000

Data Index: 204844 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 1.2784. Min Range: -1.2784

Max Act: 1.0162. Min Act: -0.0000

Data Index: 669692 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 1.2784. Min Range: -1.2784

Max Act: 1.0749. Min Act: -0.0000

Data Index: 184413 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.9298. Min Act: -0.0000

Data Index: 24665 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 1.2784. Min Range: -1.2784

Max Act: 1.0543. Min Act: -0.0000

Data Index: 666564 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.9861. Min Act: -0.0000

Data Index: 415960 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.9795. Min Act: -0.0000

Data Index: 253226 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.9808. Min Act: -0.0000

Data Index: 946339 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.9765. Min Act: -0.0000

Data Index: 165862 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1258507 (C4 (Web Text))

Max Activating Token Index: 294