Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3996 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.6793. Min Act: -0.0001

Data Index: 505521 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.6717. Min Act: -0.0000

Data Index: 898402 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5349. Min Act: -0.0001

Data Index: 369749 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5115. Min Act: -0.0001

Data Index: 496963 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1001674 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4439. Min Act: -0.0000

Data Index: 10874 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4663. Min Act: -0.0000

Data Index: 1261751 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4993. Min Act: -0.0001

Data Index: 397151 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4560. Min Act: -0.0000

Data Index: 144746 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1112323 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4374. Min Act: -0.0000

Data Index: 498661 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4523. Min Act: -0.0000

Data Index: 1013575 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4464. Min Act: -0.0000

Data Index: 883358 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4431. Min Act: -0.0000

Data Index: 705736 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4307. Min Act: -0.0000

Data Index: 638589 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1331714 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.3894. Min Act: -0.0000

Data Index: 496581 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4393. Min Act: -0.0000

Data Index: 1248590 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4640. Min Act: -0.0001

Data Index: 917511 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4657. Min Act: -0.0000

Data Index: 715632 (C4 (Web Text))

Max Activating Token Index: 888