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

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

Neuron 2657 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.3758. Min Range: -9.3758

Max Act: 9.3758. Min Act: -0.0000

Data Index: 41718 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 9.3758. Min Range: -9.3758

Max Act: 7.4951. Min Act: -0.0000

Data Index: 201798 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 9.3758. Min Range: -9.3758

Max Act: 7.2884. Min Act: -0.0000

Data Index: 569809 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 9.3758. Min Range: -9.3758

Max Act: 7.1492. Min Act: -0.0000

Data Index: 1150000 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 9.3758. Min Range: -9.3758

Max Act: 6.5326. Min Act: -0.0000

Data Index: 379810 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 9.3758. Min Range: -9.3758

Max Act: 5.5608. Min Act: -0.0000

Data Index: 346612 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 9.3758. Min Range: -9.3758

Max Act: 6.8870. Min Act: -0.0000

Data Index: 861157 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 9.3758. Min Range: -9.3758

Max Act: 8.3158. Min Act: -0.0000

Data Index: 680594 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 9.3758. Min Range: -9.3758

Max Act: 6.6096. Min Act: -0.0000

Data Index: 749843 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 9.3758. Min Range: -9.3758

Max Act: 5.8665. Min Act: -0.0000

Data Index: 282242 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 9.3758. Min Range: -9.3758

Max Act: 5.6822. Min Act: -0.0000

Data Index: 987055 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 9.3758. Min Range: -9.3758

Max Act: 6.6055. Min Act: -0.0000

Data Index: 151703 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 9.3758. Min Range: -9.3758

Max Act: 6.3524. Min Act: -0.0000

Data Index: 699808 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 9.3758. Min Range: -9.3758

Max Act: 6.0661. Min Act: -0.0000

Data Index: 555473 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 9.3758. Min Range: -9.3758

Max Act: 6.0312. Min Act: -0.0000

Data Index: 1180183 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 9.3758. Min Range: -9.3758

Max Act: 6.4026. Min Act: -0.0000

Data Index: 500451 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 9.3758. Min Range: -9.3758

Max Act: 6.1400. Min Act: -0.0000

Data Index: 218343 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 9.3758. Min Range: -9.3758

Max Act: 5.8788. Min Act: -0.0000

Data Index: 481431 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 9.3758. Min Range: -9.3758

Max Act: 5.6616. Min Act: -0.0000

Data Index: 909690 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 9.3758. Min Range: -9.3758

Max Act: 5.7896. Min Act: -0.0000

Data Index: 983909 (C4 (Web Text))

Max Activating Token Index: 550