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

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

Neuron 937 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0564. Min Range: -1.0564

Max Act: 1.0564. Min Act: -0.0000

Data Index: 738281 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.5548. Min Act: -0.0000

Data Index: 939025 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.4521. Min Act: -0.0000

Data Index: 972832 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.5981. Min Act: -0.0000

Data Index: 707530 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.5120. Min Act: -0.0000

Data Index: 182361 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.4936. Min Act: -0.0000

Data Index: 130920 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.4464. Min Act: -0.0000

Data Index: 1156855 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.4139. Min Act: -0.0000

Data Index: 48564 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.3898. Min Act: -0.0000

Data Index: 1301333 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.3688. Min Act: -0.0000

Data Index: 1318786 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1252145 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1216145 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.3961. Min Act: -0.0000

Data Index: 757170 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.3926. Min Act: -0.0000

Data Index: 335063 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.4142. Min Act: -0.0000

Data Index: 1158947 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.3654. Min Act: -0.0000

Data Index: 495890 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.3365. Min Act: -0.0000

Data Index: 953525 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.3639. Min Act: -0.0000

Data Index: 730304 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.3460. Min Act: -0.0000

Data Index: 1233786 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.3439. Min Act: -0.0000

Data Index: 792248 (C4 (Web Text))

Max Activating Token Index: 285