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

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

Neuron 5260 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.5575. Min Act: -0.0000

Data Index: 1312943 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.4803. Min Act: -0.0000

Data Index: 382982 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.4959. Min Act: -0.0000

Data Index: 283594 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.4809. Min Act: -0.0000

Data Index: 615250 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.4843. Min Act: -0.0000

Data Index: 581759 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.4849. Min Act: -0.0000

Data Index: 507340 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.4887. Min Act: -0.0000

Data Index: 173105 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.4583. Min Act: -0.0000

Data Index: 16910 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.4241. Min Act: -0.0000

Data Index: 189075 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.3697. Min Act: -0.0000

Data Index: 336422 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1130305 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.4070. Min Act: -0.0000

Data Index: 447328 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.4178. Min Act: -0.0001

Data Index: 1093643 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.4140. Min Act: -0.0000

Data Index: 367229 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.3713. Min Act: -0.0000

Data Index: 268662 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.3678. Min Act: -0.0000

Data Index: 966802 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.3782. Min Act: -0.0000

Data Index: 803902 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.3912. Min Act: -0.0000

Data Index: 640701 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.3741. Min Act: -0.0000

Data Index: 1259186 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 0.5575. Min Range: -0.5575

Max Act: 0.3826. Min Act: -0.0001

Data Index: 269473 (C4 (Web Text))

Max Activating Token Index: 485