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

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

Neuron 3551 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5139. Min Range: -2.5139

Max Act: 2.4160. Min Act: -0.0000

Data Index: 1423283 (Python Code)

Max Activating Token Index: 1017

Text #1

Max Range: 2.5139. Min Range: -2.5139

Max Act: 2.5139. Min Act: -0.0000

Data Index: 551236 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 2.5139. Min Range: -2.5139

Max Act: 2.2023. Min Act: -0.0000

Data Index: 771048 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 2.5139. Min Range: -2.5139

Max Act: 2.2964. Min Act: -0.0000

Data Index: 242284 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 2.5139. Min Range: -2.5139

Max Act: 2.2359. Min Act: -0.0000

Data Index: 686074 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 2.5139. Min Range: -2.5139

Max Act: 2.2366. Min Act: -0.0000

Data Index: 395520 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 2.5139. Min Range: -2.5139

Max Act: 2.0636. Min Act: -0.0000

Data Index: 1293113 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 2.5139. Min Range: -2.5139

Max Act: 2.2868. Min Act: -0.0000

Data Index: 1146604 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 2.5139. Min Range: -2.5139

Max Act: 2.0290. Min Act: -0.0000

Data Index: 22638 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 2.5139. Min Range: -2.5139

Max Act: 2.3453. Min Act: -0.0000

Data Index: 164156 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 2.5139. Min Range: -2.5139

Max Act: 2.0968. Min Act: -0.0000

Data Index: 482606 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 2.5139. Min Range: -2.5139

Max Act: 1.9520. Min Act: -0.0000

Data Index: 956223 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 2.5139. Min Range: -2.5139

Max Act: 2.0129. Min Act: -0.0000

Data Index: 423371 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 2.5139. Min Range: -2.5139

Max Act: 2.0195. Min Act: -0.0000

Data Index: 393075 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 2.5139. Min Range: -2.5139

Max Act: 1.8931. Min Act: -0.0000

Data Index: 374869 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 2.5139. Min Range: -2.5139

Max Act: 1.9430. Min Act: -0.0000

Data Index: 1198932 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 2.5139. Min Range: -2.5139

Max Act: 1.9555. Min Act: -0.0000

Data Index: 329882 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 2.5139. Min Range: -2.5139

Max Act: 2.0562. Min Act: -0.0000

Data Index: 746415 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 2.5139. Min Range: -2.5139

Max Act: 2.0320. Min Act: -0.0000

Data Index: 277243 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 2.5139. Min Range: -2.5139

Max Act: 1.9243. Min Act: -0.0000

Data Index: 286691 (C4 (Web Text))

Max Activating Token Index: 780