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

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

Neuron 991 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8003. Min Range: -2.8003

Max Act: 2.8003. Min Act: -0.0000

Data Index: 1459132 (Python Code)

Max Activating Token Index: 511

Text #1

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.9133. Min Act: -0.0000

Data Index: 1262229 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.7276. Min Act: -0.0000

Data Index: 700966 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.6682. Min Act: -0.0000

Data Index: 1581302 (Python Code)

Max Activating Token Index: 1020

Text #4

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.6274. Min Act: -0.0000

Data Index: 1420483 (Python Code)

Max Activating Token Index: 381

Text #5

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.5673. Min Act: -0.0000

Data Index: 1314209 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.4946. Min Act: -0.0000

Data Index: 854464 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.3902. Min Act: -0.0000

Data Index: 1405460 (Python Code)

Max Activating Token Index: 173

Text #8

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.5539. Min Act: 0.0000

Data Index: 760628 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.5046. Min Act: -0.0000

Data Index: 935920 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.4239. Min Act: -0.0000

Data Index: 725687 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.3201. Min Act: -0.0000

Data Index: 333301 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.3885. Min Act: -0.0000

Data Index: 56292 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.3892. Min Act: -0.0000

Data Index: 1023553 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.3687. Min Act: -0.0000

Data Index: 900432 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.3515. Min Act: -0.0000

Data Index: 112800 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.2722. Min Act: -0.0000

Data Index: 415737 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.3510. Min Act: -0.0000

Data Index: 907389 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.3370. Min Act: 0.0000

Data Index: 406187 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.3267. Min Act: -0.0000

Data Index: 1654617 (Python Code)

Max Activating Token Index: 77