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

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

Neuron 3403 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: 1.6069. Min Range: -1.6069

Max Act: 1.6069. Min Act: -0.0000

Data Index: 649684 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.3820. Min Act: -0.0000

Data Index: 613848 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2799. Min Act: -0.0000

Data Index: 1042326 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2236. Min Act: -0.0000

Data Index: 924647 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2567. Min Act: -0.0000

Data Index: 742943 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.1770. Min Act: -0.0000

Data Index: 438012 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2313. Min Act: -0.0000

Data Index: 593431 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.1463. Min Act: -0.0000

Data Index: 1247188 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.1534. Min Act: -0.0000

Data Index: 145274 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.1805. Min Act: -0.0000

Data Index: 532451 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.1863. Min Act: -0.0000

Data Index: 140419 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.1092. Min Act: -0.0000

Data Index: 436812 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.1959. Min Act: -0.0000

Data Index: 429957 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.1255. Min Act: -0.0000

Data Index: 577651 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.0475. Min Act: -0.0000

Data Index: 1501683 (Python Code)

Max Activating Token Index: 209

Text #15

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.0769. Min Act: -0.0000

Data Index: 475330 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.1307. Min Act: -0.0000

Data Index: 525950 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.0621. Min Act: -0.0000

Data Index: 612916 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.0162. Min Act: -0.0000

Data Index: 1592326 (Python Code)

Max Activating Token Index: 370

Text #19

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.0411. Min Act: -0.0000

Data Index: 367175 (C4 (Web Text))

Max Activating Token Index: 147