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

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

Neuron 512 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1431. Min Range: -1.1431

Max Act: 1.1069. Min Act: -0.0000

Data Index: 386500 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 1.1431. Min Range: -1.1431

Max Act: 1.1431. Min Act: -0.0000

Data Index: 251985 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 1.1431. Min Range: -1.1431

Max Act: 1.1091. Min Act: -0.0000

Data Index: 1011514 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 1.1431. Min Range: -1.1431

Max Act: 0.9848. Min Act: -0.0000

Data Index: 321440 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 1.1431. Min Range: -1.1431

Max Act: 1.0062. Min Act: -0.0000

Data Index: 1163344 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 1.1431. Min Range: -1.1431

Max Act: 0.9989. Min Act: -0.0000

Data Index: 464623 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 1.1431. Min Range: -1.1431

Max Act: 0.9444. Min Act: -0.0000

Data Index: 797661 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 1.1431. Min Range: -1.1431

Max Act: 0.8916. Min Act: -0.0000

Data Index: 712350 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 1.1431. Min Range: -1.1431

Max Act: 0.9580. Min Act: -0.0000

Data Index: 647532 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 1.1431. Min Range: -1.1431

Max Act: 0.9166. Min Act: -0.0000

Data Index: 668403 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 1.1431. Min Range: -1.1431

Max Act: 0.8714. Min Act: -0.0000

Data Index: 136379 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 1.1431. Min Range: -1.1431

Max Act: 0.9187. Min Act: -0.0000

Data Index: 608372 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 1.1431. Min Range: -1.1431

Max Act: 0.8200. Min Act: -0.0000

Data Index: 820948 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 1.1431. Min Range: -1.1431

Max Act: 0.8486. Min Act: -0.0000

Data Index: 526015 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 1.1431. Min Range: -1.1431

Max Act: 0.8702. Min Act: -0.0000

Data Index: 1024257 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 1.1431. Min Range: -1.1431

Max Act: 0.8685. Min Act: -0.0000

Data Index: 797885 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 1.1431. Min Range: -1.1431

Max Act: 0.8596. Min Act: -0.0000

Data Index: 1144071 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 1.1431. Min Range: -1.1431

Max Act: 0.8381. Min Act: -0.0000

Data Index: 1250390 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 1.1431. Min Range: -1.1431

Max Act: 0.8107. Min Act: -0.0000

Data Index: 1222040 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 1.1431. Min Range: -1.1431

Max Act: 0.8580. Min Act: -0.0000

Data Index: 1106367 (C4 (Web Text))

Max Activating Token Index: 973