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

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

Neuron 3646 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7946. Min Range: -2.7946

Max Act: 2.7946. Min Act: -0.0000

Data Index: 1016079 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 2.7946. Min Range: -2.7946

Max Act: 2.2820. Min Act: -0.0000

Data Index: 1105593 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 2.7946. Min Range: -2.7946

Max Act: 2.4636. Min Act: -0.0000

Data Index: 458780 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 2.7946. Min Range: -2.7946

Max Act: 2.2751. Min Act: -0.0000

Data Index: 581286 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 2.7946. Min Range: -2.7946

Max Act: 2.2413. Min Act: -0.0000

Data Index: 15210 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 2.7946. Min Range: -2.7946

Max Act: 2.2393. Min Act: -0.0000

Data Index: 882289 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 2.7946. Min Range: -2.7946

Max Act: 2.1269. Min Act: -0.0000

Data Index: 1065874 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 2.7946. Min Range: -2.7946

Max Act: 2.3548. Min Act: -0.0000

Data Index: 669662 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 2.7946. Min Range: -2.7946

Max Act: 2.2235. Min Act: -0.0000

Data Index: 1302608 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 2.7946. Min Range: -2.7946

Max Act: 2.2303. Min Act: -0.0000

Data Index: 1136295 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 2.7946. Min Range: -2.7946

Max Act: 2.4476. Min Act: -0.0000

Data Index: 1026559 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 2.7946. Min Range: -2.7946

Max Act: 2.1864. Min Act: -0.0000

Data Index: 1212874 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 2.7946. Min Range: -2.7946

Max Act: 2.0644. Min Act: -0.0000

Data Index: 777927 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 2.7946. Min Range: -2.7946

Max Act: 2.1576. Min Act: -0.0000

Data Index: 1059089 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 2.7946. Min Range: -2.7946

Max Act: 2.2481. Min Act: -0.0000

Data Index: 681326 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 2.7946. Min Range: -2.7946

Max Act: 2.0979. Min Act: -0.0000

Data Index: 137180 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 2.7946. Min Range: -2.7946

Max Act: 2.1049. Min Act: -0.0000

Data Index: 31983 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 2.7946. Min Range: -2.7946

Max Act: 2.0828. Min Act: -0.0000

Data Index: 507350 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 2.7946. Min Range: -2.7946

Max Act: 2.0925. Min Act: -0.0000

Data Index: 493812 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 2.7946. Min Range: -2.7946

Max Act: 2.1842. Min Act: -0.0000

Data Index: 1113511 (C4 (Web Text))

Max Activating Token Index: 807