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

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

Neuron 287 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: 2.2949. Min Range: -2.2949

Max Act: 2.2098. Min Act: -0.0000

Data Index: 920730 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 2.2949. Min Range: -2.2949

Max Act: 2.2949. Min Act: -0.0000

Data Index: 367464 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 2.2949. Min Range: -2.2949

Max Act: 2.0554. Min Act: -0.0000

Data Index: 664131 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 2.2949. Min Range: -2.2949

Max Act: 2.0109. Min Act: -0.0000

Data Index: 1147910 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 2.2949. Min Range: -2.2949

Max Act: 1.9673. Min Act: -0.0000

Data Index: 595327 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 2.2949. Min Range: -2.2949

Max Act: 1.8712. Min Act: -0.0000

Data Index: 806933 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 2.2949. Min Range: -2.2949

Max Act: 1.9835. Min Act: -0.0000

Data Index: 1043508 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 2.2949. Min Range: -2.2949

Max Act: 1.9696. Min Act: -0.0000

Data Index: 122767 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 2.2949. Min Range: -2.2949

Max Act: 1.9687. Min Act: -0.0000

Data Index: 998346 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 2.2949. Min Range: -2.2949

Max Act: 1.7666. Min Act: -0.0000

Data Index: 672196 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 2.2949. Min Range: -2.2949

Max Act: 1.8410. Min Act: -0.0000

Data Index: 258339 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 2.2949. Min Range: -2.2949

Max Act: 1.8762. Min Act: -0.0000

Data Index: 838628 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 2.2949. Min Range: -2.2949

Max Act: 1.6979. Min Act: -0.0000

Data Index: 52355 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 2.2949. Min Range: -2.2949

Max Act: 2.0028. Min Act: -0.0000

Data Index: 88193 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 2.2949. Min Range: -2.2949

Max Act: 1.7672. Min Act: -0.0000

Data Index: 126522 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 2.2949. Min Range: -2.2949

Max Act: 1.7380. Min Act: -0.0000

Data Index: 736292 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 2.2949. Min Range: -2.2949

Max Act: 1.6215. Min Act: -0.0000

Data Index: 925285 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 2.2949. Min Range: -2.2949

Max Act: 1.6994. Min Act: -0.0000

Data Index: 41617 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 2.2949. Min Range: -2.2949

Max Act: 1.6238. Min Act: -0.0000

Data Index: 1258764 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 2.2949. Min Range: -2.2949

Max Act: 1.6025. Min Act: -0.0000

Data Index: 119007 (C4 (Web Text))

Max Activating Token Index: 864