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

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

Neuron 2494 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: 1.0333. Min Range: -1.0333

Max Act: 0.9985. Min Act: -0.0001

Data Index: 53761 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 1.0333. Min Range: -1.0333

Max Act: 1.0115. Min Act: -0.0001

Data Index: 431401 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 1.0333. Min Range: -1.0333

Max Act: 1.0199. Min Act: -0.0001

Data Index: 433422 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.7981. Min Act: -0.0001

Data Index: 41708 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 1.0333. Min Range: -1.0333

Max Act: 1.0333. Min Act: -0.0001

Data Index: 888206 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.8404. Min Act: -0.0001

Data Index: 738419 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.9095. Min Act: -0.0001

Data Index: 908821 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.9522. Min Act: -0.0001

Data Index: 435283 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.8744. Min Act: -0.0001

Data Index: 1083166 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.8443. Min Act: -0.0001

Data Index: 143755 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.9477. Min Act: -0.0001

Data Index: 1170684 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.9345. Min Act: -0.0001

Data Index: 1205715 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.9020. Min Act: -0.0001

Data Index: 444212 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.8199. Min Act: -0.0001

Data Index: 908713 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.8413. Min Act: -0.0001

Data Index: 1281401 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.9135. Min Act: -0.0001

Data Index: 298130 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.8933. Min Act: -0.0001

Data Index: 784026 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.8304. Min Act: -0.0001

Data Index: 1310761 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.8218. Min Act: -0.0001

Data Index: 358554 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.7820. Min Act: -0.0001

Data Index: 1040015 (C4 (Web Text))

Max Activating Token Index: 932