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

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

Neuron 5714 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: 3.6629. Min Range: -3.6629

Max Act: 3.4951. Min Act: -0.0000

Data Index: 149774 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 3.6629. Min Range: -3.6629

Max Act: 3.6098. Min Act: -0.0000

Data Index: 962836 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 3.6629. Min Range: -3.6629

Max Act: 3.6629. Min Act: -0.0000

Data Index: 946220 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 3.6629. Min Range: -3.6629

Max Act: 3.5216. Min Act: -0.0000

Data Index: 536848 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 3.6629. Min Range: -3.6629

Max Act: 3.1309. Min Act: -0.0000

Data Index: 8818 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 3.6629. Min Range: -3.6629

Max Act: 3.0181. Min Act: -0.0000

Data Index: 926096 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.3576. Min Act: -0.0000

Data Index: 1285826 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.2900. Min Act: -0.0000

Data Index: 145763 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.0550. Min Act: -0.0000

Data Index: 153630 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.0369. Min Act: -0.0000

Data Index: 333697 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.9421. Min Act: -0.0000

Data Index: 368714 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.8972. Min Act: -0.0000

Data Index: 1120633 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.7523. Min Act: -0.0000

Data Index: 482865 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.8649. Min Act: -0.0000

Data Index: 602377 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.9476. Min Act: -0.0000

Data Index: 696532 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.6257. Min Act: -0.0000

Data Index: 109785 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.7760. Min Act: -0.0000

Data Index: 728654 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.6780. Min Act: -0.0000

Data Index: 1081097 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.6676. Min Act: -0.0000

Data Index: 922143 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.7362. Min Act: -0.0000

Data Index: 1008463 (C4 (Web Text))

Max Activating Token Index: 205