Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1167 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2247. Min Range: -1.2247

Max Act: 1.2247. Min Act: -0.0001

Data Index: 433876 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 1.2247. Min Range: -1.2247

Max Act: 1.0128. Min Act: -0.0001

Data Index: 274091 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 1.2247. Min Range: -1.2247

Max Act: 1.0132. Min Act: -0.0001

Data Index: 885040 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 1.2247. Min Range: -1.2247

Max Act: 1.0299. Min Act: -0.0001

Data Index: 519608 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 1.2247. Min Range: -1.2247

Max Act: 0.9856. Min Act: -0.0001

Data Index: 762800 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 1.2247. Min Range: -1.2247

Max Act: 0.9845. Min Act: -0.0001

Data Index: 1098880 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 1.2247. Min Range: -1.2247

Max Act: 0.9939. Min Act: -0.0001

Data Index: 525106 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 1.2247. Min Range: -1.2247

Max Act: 0.9549. Min Act: -0.0001

Data Index: 1174417 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 1.2247. Min Range: -1.2247

Max Act: 0.9185. Min Act: -0.0001

Data Index: 1305496 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 1.2247. Min Range: -1.2247

Max Act: 0.9291. Min Act: -0.0001

Data Index: 93789 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 1.2247. Min Range: -1.2247

Max Act: 0.9622. Min Act: -0.0001

Data Index: 410417 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 1.2247. Min Range: -1.2247

Max Act: 0.9478. Min Act: -0.0001

Data Index: 421464 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 1.2247. Min Range: -1.2247

Max Act: 0.9080. Min Act: -0.0001

Data Index: 935638 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 1.2247. Min Range: -1.2247

Max Act: 0.9160. Min Act: -0.0001

Data Index: 8684 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 1.2247. Min Range: -1.2247

Max Act: 0.8084. Min Act: -0.0001

Data Index: 280624 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 1.2247. Min Range: -1.2247

Max Act: 0.9026. Min Act: -0.0001

Data Index: 792192 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 1.2247. Min Range: -1.2247

Max Act: 0.8626. Min Act: -0.0001

Data Index: 753495 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 1.2247. Min Range: -1.2247

Max Act: 0.8493. Min Act: -0.0001

Data Index: 969790 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 1.2247. Min Range: -1.2247

Max Act: 0.8610. Min Act: -0.0001

Data Index: 110912 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 1.2247. Min Range: -1.2247

Max Act: 0.8260. Min Act: -0.0001

Data Index: 1217564 (C4 (Web Text))

Max Activating Token Index: 702