Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4953 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.7470. Min Act: -0.0000

Data Index: 977776 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.5975. Min Act: -0.0000

Data Index: 249760 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.6125. Min Act: -0.0000

Data Index: 584675 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.5856. Min Act: -0.0000

Data Index: 828705 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.5840. Min Act: -0.0000

Data Index: 732017 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.5900. Min Act: -0.0000

Data Index: 1245651 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.5537. Min Act: -0.0000

Data Index: 1256826 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.5746. Min Act: -0.0000

Data Index: 21357 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.5833. Min Act: -0.0000

Data Index: 254089 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.5292. Min Act: -0.0000

Data Index: 499085 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.5244. Min Act: -0.0000

Data Index: 1273916 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.5308. Min Act: -0.0000

Data Index: 539774 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.4595. Min Act: -0.0000

Data Index: 295493 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.5324. Min Act: -0.0000

Data Index: 10055 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.5499. Min Act: -0.0000

Data Index: 999044 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.5405. Min Act: -0.0000

Data Index: 240859 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1189224 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.5097. Min Act: -0.0000

Data Index: 563320 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.5484. Min Act: -0.0000

Data Index: 1256147 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1018712 (C4 (Web Text))

Max Activating Token Index: 607