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

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

Neuron 1626 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.4506. Min Act: -0.0000

Data Index: 931581 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.4250. Min Act: -0.0000

Data Index: 526155 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1238314 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.4627. Min Act: -0.0000

Data Index: 606551 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.4285. Min Act: -0.0000

Data Index: 347752 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.4111. Min Act: -0.0000

Data Index: 273191 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3795. Min Act: -0.0000

Data Index: 191041 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3820. Min Act: -0.0000

Data Index: 190838 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3800. Min Act: -0.0000

Data Index: 917457 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3761. Min Act: -0.0000

Data Index: 404999 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3531. Min Act: -0.0000

Data Index: 908880 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3508. Min Act: -0.0000

Data Index: 1018269 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3381. Min Act: -0.0000

Data Index: 436490 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3571. Min Act: -0.0000

Data Index: 1251649 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3642. Min Act: -0.0000

Data Index: 639453 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1317417 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3404. Min Act: -0.0000

Data Index: 1011277 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3517. Min Act: -0.0000

Data Index: 485706 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3628. Min Act: -0.0000

Data Index: 316181 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3483. Min Act: -0.0000

Data Index: 584474 (C4 (Web Text))

Max Activating Token Index: 516