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

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

Neuron 4760 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: 0.4814. Min Range: -0.4814

Max Act: 0.4814. Min Act: -0.0000

Data Index: 1158585 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4638. Min Act: -0.0000

Data Index: 551582 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4577. Min Act: -0.0000

Data Index: 1010708 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4061. Min Act: -0.0000

Data Index: 438323 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3844. Min Act: -0.0000

Data Index: 633556 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4166. Min Act: -0.0000

Data Index: 268430 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3811. Min Act: -0.0000

Data Index: 86368 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4638. Min Act: -0.0000

Data Index: 1264478 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3581. Min Act: -0.0000

Data Index: 971423 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3796. Min Act: -0.0000

Data Index: 923758 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3680. Min Act: -0.0000

Data Index: 105296 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3486. Min Act: -0.0000

Data Index: 1299718 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3828. Min Act: -0.0000

Data Index: 808345 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3448. Min Act: -0.0000

Data Index: 883891 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3330. Min Act: -0.0000

Data Index: 140081 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3257. Min Act: -0.0000

Data Index: 629602 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3256. Min Act: -0.0000

Data Index: 327207 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3338. Min Act: -0.0000

Data Index: 654675 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3182. Min Act: -0.0000

Data Index: 284350 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3247. Min Act: -0.0000

Data Index: 1272104 (C4 (Web Text))

Max Activating Token Index: 225