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

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

Neuron 4865 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4897. Min Range: -1.4897

Max Act: 1.4897. Min Act: -0.0000

Data Index: 633611 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 1.4897. Min Range: -1.4897

Max Act: 1.4439. Min Act: -0.0000

Data Index: 60476 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 1.4897. Min Range: -1.4897

Max Act: 1.2896. Min Act: -0.0000

Data Index: 816299 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 1.4897. Min Range: -1.4897

Max Act: 1.2062. Min Act: -0.0000

Data Index: 45486 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 1.4897. Min Range: -1.4897

Max Act: 1.2910. Min Act: -0.0000

Data Index: 751203 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 1.4897. Min Range: -1.4897

Max Act: 1.2011. Min Act: -0.0000

Data Index: 945379 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 1.4897. Min Range: -1.4897

Max Act: 1.2242. Min Act: -0.0000

Data Index: 900070 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 1.4897. Min Range: -1.4897

Max Act: 1.2386. Min Act: -0.0000

Data Index: 725591 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 1.4897. Min Range: -1.4897

Max Act: 1.1849. Min Act: -0.0000

Data Index: 324993 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.9799. Min Act: -0.0000

Data Index: 367333 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.9746. Min Act: -0.0000

Data Index: 216778 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.9168. Min Act: -0.0000

Data Index: 776660 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.9261. Min Act: -0.0000

Data Index: 632583 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.9584. Min Act: -0.0000

Data Index: 99984 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.8656. Min Act: -0.0000

Data Index: 636453 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.8858. Min Act: -0.0000

Data Index: 958483 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.9206. Min Act: -0.0000

Data Index: 432754 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.9299. Min Act: -0.0000

Data Index: 486141 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.8992. Min Act: -0.0000

Data Index: 527832 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.9528. Min Act: -0.0000

Data Index: 999572 (C4 (Web Text))

Max Activating Token Index: 699