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

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

Neuron 5799 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1545066 (Python Code)

Max Activating Token Index: 737

Text #1

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5861. Min Act: -0.0000

Data Index: 1080859 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5590. Min Act: -0.0000

Data Index: 895958 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4534. Min Act: -0.0000

Data Index: 165658 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4485. Min Act: -0.0000

Data Index: 1221003 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4419. Min Act: -0.0000

Data Index: 890387 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5302. Min Act: -0.0000

Data Index: 1179894 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4410. Min Act: -0.0000

Data Index: 231986 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4356. Min Act: -0.0000

Data Index: 54969 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3893. Min Act: -0.0000

Data Index: 1232839 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3969. Min Act: -0.0000

Data Index: 904063 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4164. Min Act: -0.0000

Data Index: 1585207 (Python Code)

Max Activating Token Index: 578

Text #12

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3485. Min Act: -0.0000

Data Index: 226108 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3425. Min Act: -0.0000

Data Index: 393715 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3678. Min Act: -0.0000

Data Index: 1628130 (Python Code)

Max Activating Token Index: 843

Text #15

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3409. Min Act: -0.0000

Data Index: 699453 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3914. Min Act: -0.0000

Data Index: 984627 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3431. Min Act: -0.0000

Data Index: 861538 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3376. Min Act: -0.0000

Data Index: 509067 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3785. Min Act: -0.0000

Data Index: 569202 (C4 (Web Text))

Max Activating Token Index: 384