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

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

Neuron 1475 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0610. Min Act: -0.0002

Data Index: 316745 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0569. Min Act: -0.0002

Data Index: 811375 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0465. Min Act: -0.0002

Data Index: 540663 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0604. Min Act: -0.0002

Data Index: 737466 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0498. Min Act: -0.0002

Data Index: 439560 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0489. Min Act: -0.0002

Data Index: 996551 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0478. Min Act: -0.0002

Data Index: 585166 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0490. Min Act: -0.0002

Data Index: 687670 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0483. Min Act: -0.0002

Data Index: 534740 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0483. Min Act: -0.0002

Data Index: 920216 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0453. Min Act: -0.0002

Data Index: 836616 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0419. Min Act: -0.0002

Data Index: 653848 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1219788 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1068991 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0437. Min Act: -0.0002

Data Index: 437476 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1325750 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0414. Min Act: -0.0002

Data Index: 983511 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0415. Min Act: -0.0002

Data Index: 972322 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0432. Min Act: -0.0002

Data Index: 646867 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0451. Min Act: -0.0002

Data Index: 45795 (C4 (Web Text))

Max Activating Token Index: 569