Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2796 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.5207. Min Act: -0.0001

Data Index: 232441 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.4893. Min Act: -0.0001

Data Index: 1214793 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.4558. Min Act: -0.0001

Data Index: 1229740 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.4383. Min Act: -0.0001

Data Index: 386317 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.4397. Min Act: -0.0001

Data Index: 925841 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.4321. Min Act: -0.0001

Data Index: 468790 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.4186. Min Act: -0.0001

Data Index: 755558 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.4091. Min Act: -0.0001

Data Index: 457667 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3683. Min Act: -0.0001

Data Index: 866536 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.4059. Min Act: -0.0001

Data Index: 387206 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3823. Min Act: -0.0001

Data Index: 1186373 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3703. Min Act: -0.0001

Data Index: 1187764 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3774. Min Act: -0.0001

Data Index: 159449 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3850. Min Act: -0.0001

Data Index: 566855 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3839. Min Act: -0.0001

Data Index: 904683 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3734. Min Act: -0.0001

Data Index: 760225 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3796. Min Act: -0.0001

Data Index: 368029 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3906. Min Act: -0.0001

Data Index: 604059 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3750. Min Act: -0.0001

Data Index: 884489 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 0.5207. Min Range: -0.5207

Max Act: 0.3665. Min Act: -0.0001

Data Index: 249396 (C4 (Web Text))

Max Activating Token Index: 865