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

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

Neuron 4411 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1934. Min Range: -2.1934

Max Act: 2.1851. Min Act: -0.0000

Data Index: 1286725 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 2.1934. Min Range: -2.1934

Max Act: 2.1133. Min Act: -0.0000

Data Index: 946193 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 2.1934. Min Range: -2.1934

Max Act: 2.1096. Min Act: -0.0000

Data Index: 505324 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 2.1934. Min Range: -2.1934

Max Act: 2.1871. Min Act: -0.0000

Data Index: 302346 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 2.1934. Min Range: -2.1934

Max Act: 2.1934. Min Act: -0.0000

Data Index: 498634 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 2.1934. Min Range: -2.1934

Max Act: 2.1326. Min Act: -0.0000

Data Index: 381150 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 2.1934. Min Range: -2.1934

Max Act: 1.8686. Min Act: -0.0000

Data Index: 8437 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 2.1934. Min Range: -2.1934

Max Act: 1.9769. Min Act: -0.0000

Data Index: 1105850 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 2.1934. Min Range: -2.1934

Max Act: 1.8581. Min Act: -0.0000

Data Index: 934535 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 2.1934. Min Range: -2.1934

Max Act: 1.8553. Min Act: -0.0000

Data Index: 1104259 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 2.1934. Min Range: -2.1934

Max Act: 1.9412. Min Act: -0.0000

Data Index: 113980 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 2.1934. Min Range: -2.1934

Max Act: 2.0473. Min Act: -0.0000

Data Index: 1069019 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 2.1934. Min Range: -2.1934

Max Act: 1.9390. Min Act: -0.0000

Data Index: 1229587 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 2.1934. Min Range: -2.1934

Max Act: 1.9296. Min Act: -0.0000

Data Index: 50747 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 2.1934. Min Range: -2.1934

Max Act: 1.8951. Min Act: -0.0000

Data Index: 25895 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 2.1934. Min Range: -2.1934

Max Act: 1.8846. Min Act: -0.0000

Data Index: 671423 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 2.1934. Min Range: -2.1934

Max Act: 1.8741. Min Act: -0.0000

Data Index: 93186 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 2.1934. Min Range: -2.1934

Max Act: 1.8732. Min Act: -0.0000

Data Index: 882207 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 2.1934. Min Range: -2.1934

Max Act: 1.8716. Min Act: -0.0000

Data Index: 1334302 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 2.1934. Min Range: -2.1934

Max Act: 1.8605. Min Act: -0.0000

Data Index: 351340 (C4 (Web Text))

Max Activating Token Index: 298