Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1279 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8379. Min Range: -1.8379

Max Act: 1.8379. Min Act: -0.0000

Data Index: 557625 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 1.8379. Min Range: -1.8379

Max Act: 1.7526. Min Act: -0.0000

Data Index: 987899 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 1.8379. Min Range: -1.8379

Max Act: 1.5200. Min Act: -0.0000

Data Index: 741444 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 1.8379. Min Range: -1.8379

Max Act: 1.4400. Min Act: -0.0000

Data Index: 979244 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 1.8379. Min Range: -1.8379

Max Act: 1.5574. Min Act: -0.0000

Data Index: 288845 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 1.8379. Min Range: -1.8379

Max Act: 1.5515. Min Act: -0.0001

Data Index: 942822 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 1.8379. Min Range: -1.8379

Max Act: 1.5501. Min Act: -0.0000

Data Index: 698617 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 1.8379. Min Range: -1.8379

Max Act: 1.5861. Min Act: -0.0001

Data Index: 577643 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 1.8379. Min Range: -1.8379

Max Act: 1.5118. Min Act: -0.0000

Data Index: 958359 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 1.8379. Min Range: -1.8379

Max Act: 1.5445. Min Act: -0.0000

Data Index: 144521 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 1.8379. Min Range: -1.8379

Max Act: 1.4137. Min Act: -0.0000

Data Index: 395150 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 1.8379. Min Range: -1.8379

Max Act: 1.5304. Min Act: -0.0000

Data Index: 1287949 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 1.8379. Min Range: -1.8379

Max Act: 1.1477. Min Act: -0.0001

Data Index: 1129461 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 1.8379. Min Range: -1.8379

Max Act: 1.4139. Min Act: -0.0000

Data Index: 618580 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 1.8379. Min Range: -1.8379

Max Act: 1.3704. Min Act: -0.0000

Data Index: 1149172 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 1.8379. Min Range: -1.8379

Max Act: 1.4030. Min Act: -0.0000

Data Index: 942663 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 1.8379. Min Range: -1.8379

Max Act: 1.3346. Min Act: -0.0000

Data Index: 772417 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 1.8379. Min Range: -1.8379

Max Act: 1.2930. Min Act: -0.0001

Data Index: 312827 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 1.8379. Min Range: -1.8379

Max Act: 1.3261. Min Act: -0.0000

Data Index: 987331 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 1.8379. Min Range: -1.8379

Max Act: 1.4446. Min Act: -0.0000

Data Index: 1251781 (C4 (Web Text))

Max Activating Token Index: 866