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

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

Neuron 811 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.8774. Min Act: -0.0001

Data Index: 130689 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.8561. Min Act: -0.0001

Data Index: 825342 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7893. Min Act: -0.0001

Data Index: 429312 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7121. Min Act: -0.0001

Data Index: 752090 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6975. Min Act: -0.0001

Data Index: 266814 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7390. Min Act: -0.0001

Data Index: 66177 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7129. Min Act: -0.0001

Data Index: 391266 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6903. Min Act: -0.0001

Data Index: 598596 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6278. Min Act: -0.0001

Data Index: 1092252 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6989. Min Act: -0.0001

Data Index: 1207713 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7140. Min Act: -0.0001

Data Index: 1207933 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6463. Min Act: -0.0001

Data Index: 447230 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6539. Min Act: -0.0001

Data Index: 654100 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6764. Min Act: -0.0001

Data Index: 393551 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6722. Min Act: -0.0001

Data Index: 1200128 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6691. Min Act: -0.0001

Data Index: 172996 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6678. Min Act: -0.0001

Data Index: 169540 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6215. Min Act: -0.0001

Data Index: 306504 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6446. Min Act: -0.0001

Data Index: 303127 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7497. Min Act: -0.0001

Data Index: 282378 (C4 (Web Text))

Max Activating Token Index: 620