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

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

Neuron 3535 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: 3.5898. Min Range: -3.5898

Max Act: 3.4802. Min Act: -0.0000

Data Index: 471773 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4555. Min Act: -0.0000

Data Index: 1089192 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.5898. Min Act: -0.0000

Data Index: 417957 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.5081. Min Act: -0.0000

Data Index: 1196107 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4084. Min Act: -0.0000

Data Index: 1184515 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.2256. Min Act: -0.0000

Data Index: 1605938 (Python Code)

Max Activating Token Index: 295

Text #6

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.3714. Min Act: -0.0000

Data Index: 957721 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.3393. Min Act: -0.0000

Data Index: 834816 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.2429. Min Act: -0.0000

Data Index: 581378 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.1949. Min Act: -0.0000

Data Index: 1123155 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.1999. Min Act: -0.0000

Data Index: 823517 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.1806. Min Act: -0.0000

Data Index: 642107 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 3.5898. Min Range: -3.5898

Max Act: 2.9933. Min Act: -0.0000

Data Index: 565741 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.0678. Min Act: -0.0000

Data Index: 831360 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.0782. Min Act: -0.0000

Data Index: 764376 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.0435. Min Act: -0.0000

Data Index: 676753 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.0359. Min Act: -0.0000

Data Index: 1622150 (Python Code)

Max Activating Token Index: 929

Text #17

Max Range: 3.5898. Min Range: -3.5898

Max Act: 2.8257. Min Act: -0.0000

Data Index: 689850 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 3.5898. Min Range: -3.5898

Max Act: 2.9784. Min Act: -0.0000

Data Index: 638548 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.1021. Min Act: -0.0000

Data Index: 384998 (C4 (Web Text))

Max Activating Token Index: 273