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

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

Neuron 831 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: 1.3666. Min Range: -1.3666

Max Act: 1.3666. Min Act: -0.0001

Data Index: 1321564 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 1.3666. Min Range: -1.3666

Max Act: 1.0749. Min Act: -0.0001

Data Index: 1135148 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 1.3666. Min Range: -1.3666

Max Act: 1.0354. Min Act: -0.0001

Data Index: 179209 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.9624. Min Act: -0.0001

Data Index: 324508 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 1.3666. Min Range: -1.3666

Max Act: 1.0538. Min Act: -0.0001

Data Index: 31771 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 1.3666. Min Range: -1.3666

Max Act: 1.0883. Min Act: -0.0001

Data Index: 783785 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.9559. Min Act: -0.0001

Data Index: 1202900 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.9265. Min Act: -0.0001

Data Index: 410811 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.9350. Min Act: -0.0001

Data Index: 532581 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.9107. Min Act: -0.0001

Data Index: 553600 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.8335. Min Act: -0.0001

Data Index: 1103541 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.8443. Min Act: -0.0001

Data Index: 364133 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.9115. Min Act: -0.0001

Data Index: 610851 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.7987. Min Act: -0.0001

Data Index: 376774 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.7936. Min Act: -0.0001

Data Index: 892051 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.8676. Min Act: -0.0001

Data Index: 34626 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.7282. Min Act: -0.0001

Data Index: 270870 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.7898. Min Act: -0.0001

Data Index: 1006476 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.8041. Min Act: -0.0001

Data Index: 1071085 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.7704. Min Act: -0.0001

Data Index: 1240870 (C4 (Web Text))

Max Activating Token Index: 850