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

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

Neuron 2188 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.8374. Min Act: -0.0000

Data Index: 284371 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.7515. Min Act: -0.0000

Data Index: 174657 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.6542. Min Act: -0.0000

Data Index: 1181203 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.7006. Min Act: -0.0000

Data Index: 1137117 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.6763. Min Act: -0.0000

Data Index: 767230 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.6197. Min Act: -0.0000

Data Index: 1293815 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.5289. Min Act: -0.0000

Data Index: 112885 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.5241. Min Act: -0.0000

Data Index: 1610683 (Python Code)

Max Activating Token Index: 762

Text #8

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1201672 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.5067. Min Act: -0.0000

Data Index: 1187149 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.5171. Min Act: -0.0000

Data Index: 1599539 (Python Code)

Max Activating Token Index: 700

Text #11

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.4743. Min Act: -0.0000

Data Index: 870739 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.4695. Min Act: -0.0000

Data Index: 1602399 (Python Code)

Max Activating Token Index: 607

Text #13

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1526646 (Python Code)

Max Activating Token Index: 428

Text #14

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.4603. Min Act: -0.0000

Data Index: 1510484 (Python Code)

Max Activating Token Index: 220

Text #15

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1375899 (Python Code)

Max Activating Token Index: 877

Text #16

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1394273 (Python Code)

Max Activating Token Index: 230

Text #17

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.4531. Min Act: -0.0000

Data Index: 1535954 (Python Code)

Max Activating Token Index: 877

Text #18

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.4985. Min Act: -0.0000

Data Index: 871249 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.4629. Min Act: -0.0000

Data Index: 440485 (C4 (Web Text))

Max Activating Token Index: 682