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

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

Neuron 2824 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.5760. Min Act: -0.0000

Data Index: 73007 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.9465. Min Act: -0.0000

Data Index: 826725 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.6386. Min Act: -0.0000

Data Index: 467219 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.5720. Min Act: -0.0000

Data Index: 701395 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.6901. Min Act: -0.0000

Data Index: 1047605 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.8290. Min Act: -0.0000

Data Index: 1053407 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.6771. Min Act: -0.0000

Data Index: 1335615 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.5437. Min Act: -0.0000

Data Index: 112431 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.6608. Min Act: -0.0000

Data Index: 189476 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.6378. Min Act: -0.0000

Data Index: 924149 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.6204. Min Act: -0.0000

Data Index: 902802 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.5994. Min Act: -0.0000

Data Index: 814427 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.5919. Min Act: -0.0000

Data Index: 842589 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.5902. Min Act: -0.0000

Data Index: 49820 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.5827. Min Act: -0.0000

Data Index: 1150748 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.5718. Min Act: -0.0000

Data Index: 131438 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.5635. Min Act: -0.0000

Data Index: 905505 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.4037. Min Act: -0.0000

Data Index: 299807 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.5053. Min Act: -0.0000

Data Index: 462359 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.5176. Min Act: -0.0000

Data Index: 581311 (C4 (Web Text))

Max Activating Token Index: 496