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

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

Neuron 1428 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1007. Min Range: -6.1007

Max Act: 6.1007. Min Act: -0.0000

Data Index: 480699 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 6.1007. Min Range: -6.1007

Max Act: 5.5089. Min Act: -0.0000

Data Index: 151491 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 6.1007. Min Range: -6.1007

Max Act: 5.6296. Min Act: -0.0000

Data Index: 227581 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 6.1007. Min Range: -6.1007

Max Act: 5.4305. Min Act: -0.0000

Data Index: 142534 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 6.1007. Min Range: -6.1007

Max Act: 5.3944. Min Act: -0.0000

Data Index: 1257036 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 6.1007. Min Range: -6.1007

Max Act: 5.4358. Min Act: -0.0000

Data Index: 407414 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 6.1007. Min Range: -6.1007

Max Act: 5.2683. Min Act: -0.0000

Data Index: 1060858 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 6.1007. Min Range: -6.1007

Max Act: 5.0761. Min Act: -0.0000

Data Index: 737545 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 6.1007. Min Range: -6.1007

Max Act: 5.2045. Min Act: -0.0000

Data Index: 1340435 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 6.1007. Min Range: -6.1007

Max Act: 5.0697. Min Act: -0.0000

Data Index: 1273859 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 6.1007. Min Range: -6.1007

Max Act: 4.2760. Min Act: -0.0000

Data Index: 760929 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 6.1007. Min Range: -6.1007

Max Act: 3.9200. Min Act: -0.0000

Data Index: 609501 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 6.1007. Min Range: -6.1007

Max Act: 3.3294. Min Act: -0.0000

Data Index: 1001942 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 6.1007. Min Range: -6.1007

Max Act: 3.3163. Min Act: -0.0000

Data Index: 385907 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 6.1007. Min Range: -6.1007

Max Act: 3.2304. Min Act: 0.0000

Data Index: 552869 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 6.1007. Min Range: -6.1007

Max Act: 3.0324. Min Act: -0.0000

Data Index: 1087821 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 6.1007. Min Range: -6.1007

Max Act: 2.7729. Min Act: -0.0000

Data Index: 956303 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 6.1007. Min Range: -6.1007

Max Act: 2.4954. Min Act: -0.0000

Data Index: 40909 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 6.1007. Min Range: -6.1007

Max Act: 2.4296. Min Act: -0.0000

Data Index: 956293 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 6.1007. Min Range: -6.1007

Max Act: 2.3965. Min Act: -0.0000

Data Index: 241392 (C4 (Web Text))

Max Activating Token Index: 991