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

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

Neuron 582 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4843. Min Act: -0.0001

Data Index: 561589 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1531074 (Python Code)

Max Activating Token Index: 199

Text #2

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4326. Min Act: -0.0001

Data Index: 103601 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4147. Min Act: -0.0001

Data Index: 103648 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4362. Min Act: -0.0001

Data Index: 735132 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3999. Min Act: -0.0001

Data Index: 1241182 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3903. Min Act: -0.0001

Data Index: 193700 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3808. Min Act: -0.0001

Data Index: 348459 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3870. Min Act: -0.0001

Data Index: 784013 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3810. Min Act: -0.0001

Data Index: 777005 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3636. Min Act: -0.0001

Data Index: 383119 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3610. Min Act: -0.0001

Data Index: 930391 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3515. Min Act: -0.0001

Data Index: 1428418 (Python Code)

Max Activating Token Index: 682

Text #13

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3787. Min Act: -0.0001

Data Index: 965721 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3363. Min Act: -0.0001

Data Index: 1080548 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3401. Min Act: -0.0001

Data Index: 824590 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3411. Min Act: -0.0001

Data Index: 960279 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3262. Min Act: -0.0001

Data Index: 560156 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3330. Min Act: -0.0001

Data Index: 450114 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.3385. Min Act: -0.0001

Data Index: 1133110 (C4 (Web Text))

Max Activating Token Index: 732