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

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

Neuron 3755 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.5818. Min Act: -0.0001

Data Index: 636171 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.5447. Min Act: -0.0001

Data Index: 26582 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.5752. Min Act: -0.0001

Data Index: 43444 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.5369. Min Act: -0.0002

Data Index: 137009 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.5572. Min Act: -0.0001

Data Index: 435432 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.5243. Min Act: -0.0002

Data Index: 952454 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.5371. Min Act: -0.0002

Data Index: 1087010 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.5218. Min Act: -0.0002

Data Index: 227273 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.5134. Min Act: -0.0002

Data Index: 482075 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.5235. Min Act: -0.0002

Data Index: 805610 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4934. Min Act: -0.0001

Data Index: 980039 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4523. Min Act: -0.0002

Data Index: 443447 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4554. Min Act: -0.0002

Data Index: 1023550 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4839. Min Act: -0.0002

Data Index: 1008990 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4668. Min Act: -0.0002

Data Index: 389 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4771. Min Act: -0.0002

Data Index: 447971 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4742. Min Act: -0.0001

Data Index: 537118 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4715. Min Act: -0.0001

Data Index: 1145071 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4642. Min Act: -0.0002

Data Index: 940606 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4594. Min Act: -0.0001

Data Index: 890527 (C4 (Web Text))

Max Activating Token Index: 500