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

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

Neuron 3090 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1711. Min Range: -1.1711

Max Act: 1.1711. Min Act: -0.0000

Data Index: 622754 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 1.1711. Min Range: -1.1711

Max Act: 1.1493. Min Act: -0.0000

Data Index: 1168139 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 1.1711. Min Range: -1.1711

Max Act: 1.0146. Min Act: -0.0001

Data Index: 1248518 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 1.1711. Min Range: -1.1711

Max Act: 0.9908. Min Act: -0.0001

Data Index: 687277 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 1.1711. Min Range: -1.1711

Max Act: 0.9572. Min Act: -0.0000

Data Index: 247040 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 1.1711. Min Range: -1.1711

Max Act: 0.9532. Min Act: -0.0001

Data Index: 148900 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 1.1711. Min Range: -1.1711

Max Act: 0.9059. Min Act: -0.0000

Data Index: 237283 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 1.1711. Min Range: -1.1711

Max Act: 0.9139. Min Act: -0.0000

Data Index: 1215913 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 1.1711. Min Range: -1.1711

Max Act: 0.9328. Min Act: -0.0001

Data Index: 1030073 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 1.1711. Min Range: -1.1711

Max Act: 0.8301. Min Act: -0.0000

Data Index: 763552 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 1.1711. Min Range: -1.1711

Max Act: 0.8187. Min Act: -0.0000

Data Index: 1032492 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 1.1711. Min Range: -1.1711

Max Act: 0.8323. Min Act: -0.0001

Data Index: 845617 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 1.1711. Min Range: -1.1711

Max Act: 0.8342. Min Act: -0.0001

Data Index: 579240 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 1.1711. Min Range: -1.1711

Max Act: 0.8006. Min Act: -0.0000

Data Index: 234871 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 1.1711. Min Range: -1.1711

Max Act: 0.8521. Min Act: -0.0000

Data Index: 1337789 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 1.1711. Min Range: -1.1711

Max Act: 0.8265. Min Act: -0.0000

Data Index: 361620 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 1.1711. Min Range: -1.1711

Max Act: 0.7654. Min Act: -0.0000

Data Index: 304014 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 1.1711. Min Range: -1.1711

Max Act: 0.7776. Min Act: -0.0000

Data Index: 735070 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 1.1711. Min Range: -1.1711

Max Act: 0.7733. Min Act: -0.0001

Data Index: 570792 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 1.1711. Min Range: -1.1711

Max Act: 0.7604. Min Act: -0.0000

Data Index: 585631 (C4 (Web Text))

Max Activating Token Index: 494