Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3934 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.6502. Min Act: -0.0000

Data Index: 1396308 (Python Code)

Max Activating Token Index: 238

Text #1

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1234540 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.6810. Min Act: -0.0000

Data Index: 1129790 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.5801. Min Act: -0.0000

Data Index: 735238 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.6417. Min Act: -0.0000

Data Index: 892809 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.6435. Min Act: -0.0000

Data Index: 35679 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.5824. Min Act: -0.0000

Data Index: 865395 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.6294. Min Act: -0.0000

Data Index: 1401494 (Python Code)

Max Activating Token Index: 269

Text #8

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.5686. Min Act: -0.0000

Data Index: 1571661 (Python Code)

Max Activating Token Index: 440

Text #9

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.5870. Min Act: 0.0000

Data Index: 1460091 (Python Code)

Max Activating Token Index: 404

Text #10

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.5457. Min Act: -0.0000

Data Index: 712748 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.5774. Min Act: 0.0000

Data Index: 1426879 (Python Code)

Max Activating Token Index: 367

Text #12

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.5696. Min Act: -0.0000

Data Index: 229773 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1536562 (Python Code)

Max Activating Token Index: 751

Text #14

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.5534. Min Act: -0.0000

Data Index: 1425497 (Python Code)

Max Activating Token Index: 213

Text #15

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.5073. Min Act: -0.0000

Data Index: 861259 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.5470. Min Act: -0.0000

Data Index: 833701 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.5040. Min Act: -0.0000

Data Index: 966005 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.5297. Min Act: -0.0000

Data Index: 412616 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.5372. Min Act: -0.0000

Data Index: 1401051 (Python Code)

Max Activating Token Index: 491