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

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

Neuron 3427 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.5661. Min Act: -0.0000

Data Index: 462333 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.4370. Min Act: -0.0000

Data Index: 812587 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.4918. Min Act: -0.0000

Data Index: 834308 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.4048. Min Act: -0.0000

Data Index: 999641 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.3746. Min Act: -0.0000

Data Index: 313205 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.4505. Min Act: -0.0000

Data Index: 259158 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.3142. Min Act: -0.0000

Data Index: 191292 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.3382. Min Act: -0.0000

Data Index: 569669 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.2756. Min Act: -0.0000

Data Index: 434327 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.2497. Min Act: -0.0000

Data Index: 843828 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.2111. Min Act: -0.0000

Data Index: 854267 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.2735. Min Act: -0.0000

Data Index: 1167394 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.1757. Min Act: -0.0000

Data Index: 1254690 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.2137. Min Act: -0.0000

Data Index: 831217 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.2118. Min Act: -0.0000

Data Index: 631139 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.1627. Min Act: -0.0000

Data Index: 942989 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.1932. Min Act: -0.0000

Data Index: 165124 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.1418. Min Act: -0.0000

Data Index: 636819 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.1839. Min Act: -0.0000

Data Index: 585811 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.1246. Min Act: -0.0000

Data Index: 316846 (C4 (Web Text))

Max Activating Token Index: 799