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

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

Neuron 1749 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.3305. Min Act: -0.0000

Data Index: 358257 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.2104. Min Act: 0.0000

Data Index: 671414 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.2570. Min Act: -0.0000

Data Index: 918853 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0544. Min Act: -0.0000

Data Index: 1294315 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0481. Min Act: -0.0000

Data Index: 275101 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 1.3305. Min Range: -1.3305

Max Act: 0.9925. Min Act: -0.0000

Data Index: 409811 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0466. Min Act: -0.0000

Data Index: 1149631 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 1.3305. Min Range: -1.3305

Max Act: 0.9766. Min Act: -0.0000

Data Index: 98681 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 1.3305. Min Range: -1.3305

Max Act: 0.9529. Min Act: -0.0000

Data Index: 653129 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0167. Min Act: -0.0000

Data Index: 667651 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 1.3305. Min Range: -1.3305

Max Act: 0.9976. Min Act: -0.0000

Data Index: 893227 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 1.3305. Min Range: -1.3305

Max Act: 0.9254. Min Act: -0.0000

Data Index: 610066 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 1.3305. Min Range: -1.3305

Max Act: 0.9270. Min Act: -0.0000

Data Index: 1133806 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 1.3305. Min Range: -1.3305

Max Act: 0.8913. Min Act: -0.0000

Data Index: 528553 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 1.3305. Min Range: -1.3305

Max Act: 0.8894. Min Act: -0.0000

Data Index: 810400 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 1.3305. Min Range: -1.3305

Max Act: 0.8867. Min Act: -0.0000

Data Index: 1258132 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 1.3305. Min Range: -1.3305

Max Act: 0.8339. Min Act: -0.0000

Data Index: 171685 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 1.3305. Min Range: -1.3305

Max Act: 0.9299. Min Act: -0.0000

Data Index: 1139515 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 1.3305. Min Range: -1.3305

Max Act: 0.9876. Min Act: -0.0000

Data Index: 1320338 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 1.3305. Min Range: -1.3305

Max Act: 0.8729. Min Act: -0.0000

Data Index: 342089 (C4 (Web Text))

Max Activating Token Index: 736