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

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

Neuron 4582 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: 1.2642. Min Range: -1.2642

Max Act: 1.2642. Min Act: -0.0000

Data Index: 300080 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 1.2642. Min Range: -1.2642

Max Act: 1.1723. Min Act: -0.0000

Data Index: 1346429 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 1.2642. Min Range: -1.2642

Max Act: 1.1122. Min Act: -0.0000

Data Index: 552426 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 1.2642. Min Range: -1.2642

Max Act: 1.0710. Min Act: -0.0000

Data Index: 220059 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 1.2642. Min Range: -1.2642

Max Act: 0.9825. Min Act: -0.0000

Data Index: 866862 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 1.2642. Min Range: -1.2642

Max Act: 0.9494. Min Act: -0.0000

Data Index: 572463 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 1.2642. Min Range: -1.2642

Max Act: 1.0384. Min Act: -0.0000

Data Index: 291138 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 1.2642. Min Range: -1.2642

Max Act: 0.9897. Min Act: -0.0000

Data Index: 1327345 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 1.2642. Min Range: -1.2642

Max Act: 0.9909. Min Act: -0.0000

Data Index: 383492 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 1.2642. Min Range: -1.2642

Max Act: 0.9114. Min Act: -0.0000

Data Index: 38040 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 1.2642. Min Range: -1.2642

Max Act: 0.8439. Min Act: -0.0000

Data Index: 603385 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 1.2642. Min Range: -1.2642

Max Act: 0.8097. Min Act: 0.0000

Data Index: 1165020 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 1.2642. Min Range: -1.2642

Max Act: 0.8571. Min Act: -0.0000

Data Index: 485093 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 1.2642. Min Range: -1.2642

Max Act: 0.8562. Min Act: -0.0000

Data Index: 46833 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 1.2642. Min Range: -1.2642

Max Act: 0.8320. Min Act: -0.0000

Data Index: 1078425 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 1.2642. Min Range: -1.2642

Max Act: 0.8879. Min Act: -0.0000

Data Index: 530904 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 1.2642. Min Range: -1.2642

Max Act: 0.8305. Min Act: -0.0000

Data Index: 227171 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 1.2642. Min Range: -1.2642

Max Act: 0.8270. Min Act: -0.0000

Data Index: 1002071 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 1.2642. Min Range: -1.2642

Max Act: 0.7690. Min Act: -0.0000

Data Index: 903290 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 1.2642. Min Range: -1.2642

Max Act: 0.8730. Min Act: -0.0000

Data Index: 1111387 (C4 (Web Text))

Max Activating Token Index: 809