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

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

Neuron 1553 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4001. Min Range: -2.4001

Max Act: 2.4001. Min Act: -0.0000

Data Index: 1120082 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 2.4001. Min Range: -2.4001

Max Act: 1.9175. Min Act: -0.0001

Data Index: 308539 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 2.4001. Min Range: -2.4001

Max Act: 1.7097. Min Act: -0.0001

Data Index: 409331 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 2.4001. Min Range: -2.4001

Max Act: 1.6658. Min Act: -0.0000

Data Index: 1095466 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 2.4001. Min Range: -2.4001

Max Act: 1.5536. Min Act: -0.0000

Data Index: 332620 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 2.4001. Min Range: -2.4001

Max Act: 1.6032. Min Act: -0.0000

Data Index: 894184 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 2.4001. Min Range: -2.4001

Max Act: 1.6840. Min Act: -0.0000

Data Index: 532810 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 2.4001. Min Range: -2.4001

Max Act: 1.5041. Min Act: -0.0000

Data Index: 159574 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 2.4001. Min Range: -2.4001

Max Act: 1.6417. Min Act: -0.0000

Data Index: 237420 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 2.4001. Min Range: -2.4001

Max Act: 1.4516. Min Act: -0.0000

Data Index: 695936 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 2.4001. Min Range: -2.4001

Max Act: 1.3653. Min Act: -0.0000

Data Index: 1314525 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 2.4001. Min Range: -2.4001

Max Act: 1.6179. Min Act: -0.0000

Data Index: 1276112 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 2.4001. Min Range: -2.4001

Max Act: 1.3968. Min Act: -0.0000

Data Index: 342229 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 2.4001. Min Range: -2.4001

Max Act: 1.4224. Min Act: -0.0000

Data Index: 447558 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 2.4001. Min Range: -2.4001

Max Act: 1.4288. Min Act: -0.0000

Data Index: 701108 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 2.4001. Min Range: -2.4001

Max Act: 1.4907. Min Act: -0.0001

Data Index: 630694 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 2.4001. Min Range: -2.4001

Max Act: 1.3235. Min Act: -0.0000

Data Index: 111571 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 2.4001. Min Range: -2.4001

Max Act: 1.4375. Min Act: -0.0000

Data Index: 1225737 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 2.4001. Min Range: -2.4001

Max Act: 1.3876. Min Act: -0.0000

Data Index: 416655 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 2.4001. Min Range: -2.4001

Max Act: 1.3591. Min Act: -0.0000

Data Index: 540967 (C4 (Web Text))

Max Activating Token Index: 839