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

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

Neuron 3532 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: 6.0408. Min Range: -6.0408

Max Act: 6.0408. Min Act: -0.0000

Data Index: 464407 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 6.0408. Min Range: -6.0408

Max Act: 5.9016. Min Act: -0.0000

Data Index: 137445 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 6.0408. Min Range: -6.0408

Max Act: 5.4962. Min Act: -0.0000

Data Index: 834239 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 6.0408. Min Range: -6.0408

Max Act: 5.3297. Min Act: -0.0000

Data Index: 17288 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 6.0408. Min Range: -6.0408

Max Act: 5.6631. Min Act: -0.0000

Data Index: 1122708 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 6.0408. Min Range: -6.0408

Max Act: 4.3399. Min Act: -0.0000

Data Index: 808014 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 6.0408. Min Range: -6.0408

Max Act: 4.5858. Min Act: -0.0000

Data Index: 726344 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 6.0408. Min Range: -6.0408

Max Act: 4.4149. Min Act: -0.0000

Data Index: 850199 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 6.0408. Min Range: -6.0408

Max Act: 4.2023. Min Act: -0.0000

Data Index: 428732 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 6.0408. Min Range: -6.0408

Max Act: 4.0394. Min Act: -0.0000

Data Index: 580696 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 6.0408. Min Range: -6.0408

Max Act: 3.8435. Min Act: -0.0000

Data Index: 459241 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 6.0408. Min Range: -6.0408

Max Act: 4.1682. Min Act: -0.0000

Data Index: 493296 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 6.0408. Min Range: -6.0408

Max Act: 3.6223. Min Act: -0.0000

Data Index: 1204837 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 6.0408. Min Range: -6.0408

Max Act: 3.7712. Min Act: -0.0000

Data Index: 57330 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 6.0408. Min Range: -6.0408

Max Act: 4.0717. Min Act: -0.0000

Data Index: 29967 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 6.0408. Min Range: -6.0408

Max Act: 3.9328. Min Act: -0.0000

Data Index: 922158 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 6.0408. Min Range: -6.0408

Max Act: 3.7725. Min Act: -0.0000

Data Index: 1127468 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 6.0408. Min Range: -6.0408

Max Act: 3.7696. Min Act: -0.0000

Data Index: 1079176 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 6.0408. Min Range: -6.0408

Max Act: 3.7337. Min Act: -0.0000

Data Index: 1130386 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 6.0408. Min Range: -6.0408

Max Act: 3.7569. Min Act: -0.0000

Data Index: 606648 (C4 (Web Text))

Max Activating Token Index: 292