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

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

Neuron 1033 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: 1.2473. Min Range: -1.2473

Max Act: 1.2473. Min Act: -0.0000

Data Index: 1333576 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 1.2473. Min Range: -1.2473

Max Act: 1.1226. Min Act: -0.0000

Data Index: 484237 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 1.2473. Min Range: -1.2473

Max Act: 1.0421. Min Act: -0.0000

Data Index: 1090575 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 1.2473. Min Range: -1.2473

Max Act: 1.0164. Min Act: -0.0000

Data Index: 247314 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 1.2473. Min Range: -1.2473

Max Act: 0.9667. Min Act: -0.0000

Data Index: 216914 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 1.2473. Min Range: -1.2473

Max Act: 1.0134. Min Act: -0.0000

Data Index: 614120 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 1.2473. Min Range: -1.2473

Max Act: 0.9785. Min Act: -0.0000

Data Index: 967028 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 1.2473. Min Range: -1.2473

Max Act: 0.9813. Min Act: -0.0000

Data Index: 687721 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 1.2473. Min Range: -1.2473

Max Act: 0.9489. Min Act: -0.0000

Data Index: 282143 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 1.2473. Min Range: -1.2473

Max Act: 0.9198. Min Act: -0.0000

Data Index: 162514 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 1.2473. Min Range: -1.2473

Max Act: 0.8899. Min Act: -0.0000

Data Index: 395143 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 1.2473. Min Range: -1.2473

Max Act: 0.8939. Min Act: -0.0000

Data Index: 1224543 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 1.2473. Min Range: -1.2473

Max Act: 0.8517. Min Act: -0.0000

Data Index: 679437 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 1.2473. Min Range: -1.2473

Max Act: 0.8506. Min Act: -0.0000

Data Index: 944013 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 1.2473. Min Range: -1.2473

Max Act: 0.8326. Min Act: -0.0000

Data Index: 782942 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 1.2473. Min Range: -1.2473

Max Act: 0.8402. Min Act: -0.0000

Data Index: 291722 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 1.2473. Min Range: -1.2473

Max Act: 0.8261. Min Act: -0.0000

Data Index: 279539 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 1.2473. Min Range: -1.2473

Max Act: 0.8460. Min Act: -0.0000

Data Index: 425447 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 1.2473. Min Range: -1.2473

Max Act: 0.7949. Min Act: -0.0000

Data Index: 1068695 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 1.2473. Min Range: -1.2473

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1652457 (Python Code)

Max Activating Token Index: 950