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

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

Neuron 1788 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1446. Min Range: -5.1446

Max Act: 5.1446. Min Act: -0.0001

Data Index: 1151943 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 5.1446. Min Range: -5.1446

Max Act: 4.9928. Min Act: -0.0000

Data Index: 767397 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 5.1446. Min Range: -5.1446

Max Act: 4.9716. Min Act: -0.0001

Data Index: 1299933 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 5.1446. Min Range: -5.1446

Max Act: 4.6645. Min Act: -0.0001

Data Index: 645159 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 5.1446. Min Range: -5.1446

Max Act: 4.5980. Min Act: -0.0001

Data Index: 148108 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 5.1446. Min Range: -5.1446

Max Act: 4.5248. Min Act: -0.0001

Data Index: 240834 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 5.1446. Min Range: -5.1446

Max Act: 4.4303. Min Act: -0.0000

Data Index: 855067 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 5.1446. Min Range: -5.1446

Max Act: 4.4166. Min Act: -0.0000

Data Index: 1170151 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 5.1446. Min Range: -5.1446

Max Act: 4.4886. Min Act: -0.0001

Data Index: 279799 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 5.1446. Min Range: -5.1446

Max Act: 3.9724. Min Act: -0.0001

Data Index: 1293802 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 5.1446. Min Range: -5.1446

Max Act: 4.0221. Min Act: -0.0001

Data Index: 952982 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 5.1446. Min Range: -5.1446

Max Act: 3.9908. Min Act: -0.0000

Data Index: 1056606 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 5.1446. Min Range: -5.1446

Max Act: 3.8725. Min Act: -0.0001

Data Index: 1178534 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 5.1446. Min Range: -5.1446

Max Act: 3.8390. Min Act: -0.0000

Data Index: 493837 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 5.1446. Min Range: -5.1446

Max Act: 3.8098. Min Act: -0.0001

Data Index: 729432 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 5.1446. Min Range: -5.1446

Max Act: 4.1301. Min Act: -0.0001

Data Index: 831203 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 5.1446. Min Range: -5.1446

Max Act: 4.0944. Min Act: -0.0001

Data Index: 934773 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 5.1446. Min Range: -5.1446

Max Act: 4.0649. Min Act: -0.0001

Data Index: 436600 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 5.1446. Min Range: -5.1446

Max Act: 3.5695. Min Act: -0.0001

Data Index: 828431 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 5.1446. Min Range: -5.1446

Max Act: 3.8290. Min Act: -0.0001

Data Index: 681364 (C4 (Web Text))

Max Activating Token Index: 262