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

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

Neuron 4610 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1067792 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.6132. Min Act: -0.0000

Data Index: 917296 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.4457. Min Act: -0.0000

Data Index: 233750 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5308. Min Act: -0.0000

Data Index: 1639733 (Python Code)

Max Activating Token Index: 726

Text #4

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5033. Min Act: -0.0000

Data Index: 275748 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5022. Min Act: -0.0000

Data Index: 1186529 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5242. Min Act: -0.0000

Data Index: 453212 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5226. Min Act: -0.0000

Data Index: 77539 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5168. Min Act: -0.0000

Data Index: 546576 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5126. Min Act: -0.0000

Data Index: 958543 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5271. Min Act: -0.0000

Data Index: 960534 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.4424. Min Act: -0.0000

Data Index: 158560 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5384. Min Act: -0.0000

Data Index: 593524 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5336. Min Act: -0.0000

Data Index: 1153196 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.4900. Min Act: -0.0000

Data Index: 100763 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.4856. Min Act: -0.0000

Data Index: 1189963 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.4973. Min Act: -0.0000

Data Index: 325369 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.4815. Min Act: -0.0000

Data Index: 85312 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5151. Min Act: -0.0000

Data Index: 272992 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.4896. Min Act: -0.0000

Data Index: 384451 (C4 (Web Text))

Max Activating Token Index: 888