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

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

Neuron 2002 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.3037. Min Act: -0.0002

Data Index: 205885 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2827. Min Act: -0.0002

Data Index: 849174 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2801. Min Act: -0.0003

Data Index: 1287007 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2724. Min Act: -0.0003

Data Index: 718282 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2769. Min Act: -0.0003

Data Index: 413673 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2716. Min Act: -0.0003

Data Index: 1242261 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2556. Min Act: -0.0003

Data Index: 167909 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2573. Min Act: -0.0003

Data Index: 1116848 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2538. Min Act: -0.0003

Data Index: 287930 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2538. Min Act: -0.0003

Data Index: 637809 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2593. Min Act: -0.0003

Data Index: 633953 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2465. Min Act: -0.0003

Data Index: 272719 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2503. Min Act: -0.0003

Data Index: 750356 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2410. Min Act: -0.0002

Data Index: 87662 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2478. Min Act: -0.0002

Data Index: 779633 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2483. Min Act: -0.0003

Data Index: 788403 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2476. Min Act: -0.0003

Data Index: 1288379 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2446. Min Act: -0.0003

Data Index: 754526 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2507. Min Act: -0.0003

Data Index: 1229885 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2422. Min Act: -0.0003

Data Index: 1305600 (C4 (Web Text))

Max Activating Token Index: 279