Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3772 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.7473. Min Act: -0.0000

Data Index: 1251979 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.6699. Min Act: -0.0001

Data Index: 1307602 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.7021. Min Act: -0.0000

Data Index: 514264 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.6888. Min Act: -0.0000

Data Index: 436274 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.6184. Min Act: -0.0000

Data Index: 602770 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.6734. Min Act: -0.0000

Data Index: 551772 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.5754. Min Act: -0.0001

Data Index: 313449 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.5181. Min Act: -0.0000

Data Index: 733638 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.5492. Min Act: -0.0000

Data Index: 1342608 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.6096. Min Act: -0.0000

Data Index: 211633 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.4733. Min Act: -0.0000

Data Index: 238878 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.5196. Min Act: -0.0000

Data Index: 910818 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.3646. Min Act: -0.0000

Data Index: 1349423 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.4293. Min Act: -0.0001

Data Index: 192467 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.3336. Min Act: -0.0001

Data Index: 500314 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.3157. Min Act: -0.0000

Data Index: 660441 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.3948. Min Act: -0.0000

Data Index: 379487 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.3144. Min Act: -0.0000

Data Index: 521585 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.3695. Min Act: -0.0000

Data Index: 1266774 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.2946. Min Act: -0.0000

Data Index: 782034 (C4 (Web Text))

Max Activating Token Index: 99