Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1514 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.9710. Min Act: -0.0001

Data Index: 868638 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8996. Min Act: -0.0001

Data Index: 655966 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8476. Min Act: -0.0001

Data Index: 620550 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8627. Min Act: -0.0001

Data Index: 1252500 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8257. Min Act: -0.0001

Data Index: 598538 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7986. Min Act: -0.0001

Data Index: 488786 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8449. Min Act: -0.0001

Data Index: 37475 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7943. Min Act: -0.0001

Data Index: 522891 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8067. Min Act: -0.0001

Data Index: 178718 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8047. Min Act: -0.0001

Data Index: 1064845 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8301. Min Act: -0.0001

Data Index: 364083 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8173. Min Act: -0.0001

Data Index: 942193 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7916. Min Act: -0.0001

Data Index: 750399 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7963. Min Act: -0.0001

Data Index: 349158 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7878. Min Act: -0.0001

Data Index: 35669 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7984. Min Act: -0.0001

Data Index: 1283376 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8159. Min Act: -0.0001

Data Index: 817431 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7630. Min Act: -0.0001

Data Index: 1284867 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7843. Min Act: -0.0001

Data Index: 396532 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7786. Min Act: -0.0001

Data Index: 183 (C4 (Web Text))

Max Activating Token Index: 951