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

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

Neuron 2299 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: 3.9528. Min Range: -3.9528

Max Act: 3.9528. Min Act: -0.0000

Data Index: 962505 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.8870. Min Act: -0.0000

Data Index: 467346 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.5014. Min Act: -0.0000

Data Index: 1123618 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 3.9528. Min Range: -3.9528

Max Act: 2.9671. Min Act: -0.0000

Data Index: 311922 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.3455. Min Act: -0.0000

Data Index: 444058 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 3.9528. Min Range: -3.9528

Max Act: 3.0177. Min Act: -0.0000

Data Index: 331625 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 3.9528. Min Range: -3.9528

Max Act: 2.6986. Min Act: -0.0000

Data Index: 1140199 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 3.9528. Min Range: -3.9528

Max Act: 2.8081. Min Act: -0.0000

Data Index: 1164043 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 3.9528. Min Range: -3.9528

Max Act: 2.6347. Min Act: -0.0000

Data Index: 912815 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 3.9528. Min Range: -3.9528

Max Act: 2.7554. Min Act: -0.0000

Data Index: 452145 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 3.9528. Min Range: -3.9528

Max Act: 2.6890. Min Act: -0.0000

Data Index: 215177 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 3.9528. Min Range: -3.9528

Max Act: 2.6864. Min Act: -0.0000

Data Index: 51393 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 3.9528. Min Range: -3.9528

Max Act: 2.6152. Min Act: -0.0000

Data Index: 573040 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 3.9528. Min Range: -3.9528

Max Act: 2.6124. Min Act: -0.0000

Data Index: 868352 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 3.9528. Min Range: -3.9528

Max Act: 2.4873. Min Act: -0.0000

Data Index: 262169 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 3.9528. Min Range: -3.9528

Max Act: 2.2601. Min Act: -0.0000

Data Index: 285488 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 3.9528. Min Range: -3.9528

Max Act: 2.4915. Min Act: -0.0000

Data Index: 1344576 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 3.9528. Min Range: -3.9528

Max Act: 2.5021. Min Act: -0.0000

Data Index: 232228 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 3.9528. Min Range: -3.9528

Max Act: 2.3515. Min Act: -0.0000

Data Index: 938552 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 3.9528. Min Range: -3.9528

Max Act: 2.4600. Min Act: -0.0000

Data Index: 462466 (C4 (Web Text))

Max Activating Token Index: 497