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

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

Neuron 4836 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0956. Min Range: -1.0956

Max Act: 1.0956. Min Act: -0.0000

Data Index: 518734 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 1.0956. Min Range: -1.0956

Max Act: 1.0276. Min Act: -0.0000

Data Index: 1017743 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 1.0956. Min Range: -1.0956

Max Act: 0.9477. Min Act: -0.0000

Data Index: 707917 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 1.0956. Min Range: -1.0956

Max Act: 0.8870. Min Act: -0.0000

Data Index: 1546168 (Python Code)

Max Activating Token Index: 611

Text #4

Max Range: 1.0956. Min Range: -1.0956

Max Act: 0.9166. Min Act: -0.0000

Data Index: 104223 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 1.0956. Min Range: -1.0956

Max Act: 0.9027. Min Act: -0.0000

Data Index: 627399 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 1.0956. Min Range: -1.0956

Max Act: 0.8576. Min Act: -0.0000

Data Index: 1167832 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 1.0956. Min Range: -1.0956

Max Act: 0.8494. Min Act: -0.0000

Data Index: 1342339 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 1.0956. Min Range: -1.0956

Max Act: 0.8966. Min Act: -0.0000

Data Index: 1357713 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 1.0956. Min Range: -1.0956

Max Act: 0.8772. Min Act: -0.0000

Data Index: 410626 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 1.0956. Min Range: -1.0956

Max Act: 0.7721. Min Act: -0.0000

Data Index: 201580 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 1.0956. Min Range: -1.0956

Max Act: 0.7765. Min Act: -0.0000

Data Index: 347683 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 1.0956. Min Range: -1.0956

Max Act: 0.8426. Min Act: -0.0000

Data Index: 1529541 (Python Code)

Max Activating Token Index: 804

Text #13

Max Range: 1.0956. Min Range: -1.0956

Max Act: 0.8480. Min Act: -0.0000

Data Index: 1400277 (Python Code)

Max Activating Token Index: 401

Text #14

Max Range: 1.0956. Min Range: -1.0956

Max Act: 0.7645. Min Act: -0.0000

Data Index: 462366 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 1.0956. Min Range: -1.0956

Max Act: 0.8105. Min Act: -0.0000

Data Index: 46594 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 1.0956. Min Range: -1.0956

Max Act: 0.7375. Min Act: -0.0000

Data Index: 636848 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 1.0956. Min Range: -1.0956

Max Act: 0.8593. Min Act: -0.0000

Data Index: 1423767 (Python Code)

Max Activating Token Index: 468

Text #18

Max Range: 1.0956. Min Range: -1.0956

Max Act: 0.7374. Min Act: -0.0000

Data Index: 109217 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 1.0956. Min Range: -1.0956

Max Act: 0.8328. Min Act: -0.0000

Data Index: 1433894 (Python Code)

Max Activating Token Index: 315