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

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

Neuron 4731 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1647. Min Range: -1.1647

Max Act: 1.1647. Min Act: -0.0000

Data Index: 15517 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.9478. Min Act: -0.0000

Data Index: 843331 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1012079 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.7636. Min Act: -0.0000

Data Index: 1114849 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.7570. Min Act: -0.0000

Data Index: 803890 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.7386. Min Act: -0.0000

Data Index: 924938 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.7236. Min Act: -0.0000

Data Index: 290145 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.7679. Min Act: -0.0000

Data Index: 621447 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.7296. Min Act: -0.0000

Data Index: 526949 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.7094. Min Act: -0.0000

Data Index: 756880 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.7210. Min Act: -0.0000

Data Index: 602011 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.6876. Min Act: -0.0000

Data Index: 253353 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.6752. Min Act: -0.0000

Data Index: 538153 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.6914. Min Act: -0.0000

Data Index: 200811 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.6384. Min Act: -0.0000

Data Index: 1335857 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.6747. Min Act: -0.0000

Data Index: 230688 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.6231. Min Act: -0.0000

Data Index: 204701 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.6473. Min Act: -0.0000

Data Index: 600225 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.6291. Min Act: -0.0000

Data Index: 858871 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.6067. Min Act: -0.0000

Data Index: 711897 (C4 (Web Text))

Max Activating Token Index: 320