Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 194 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2536. Min Act: -0.0001

Data Index: 250203 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2496. Min Act: -0.0001

Data Index: 796060 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2452. Min Act: -0.0001

Data Index: 638889 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2613. Min Act: -0.0001

Data Index: 324423 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2133. Min Act: -0.0001

Data Index: 375276 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2298. Min Act: -0.0001

Data Index: 1160487 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2225. Min Act: -0.0001

Data Index: 1270581 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2315. Min Act: -0.0001

Data Index: 908310 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2374. Min Act: -0.0001

Data Index: 870758 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2243. Min Act: -0.0001

Data Index: 437121 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2216. Min Act: -0.0001

Data Index: 29736 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2228. Min Act: -0.0001

Data Index: 298212 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2277. Min Act: -0.0001

Data Index: 190601 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2184. Min Act: -0.0001

Data Index: 1086192 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2157. Min Act: -0.0001

Data Index: 1019348 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2022. Min Act: -0.0001

Data Index: 764455 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2146. Min Act: -0.0001

Data Index: 20298 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2123. Min Act: -0.0001

Data Index: 83251 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2194. Min Act: -0.0001

Data Index: 395209 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2035. Min Act: -0.0001

Data Index: 1040503 (C4 (Web Text))

Max Activating Token Index: 46