Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2554 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0593. Min Act: -0.0004

Data Index: 59003 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0610. Min Act: -0.0004

Data Index: 66904 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0585. Min Act: -0.0004

Data Index: 847889 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0592. Min Act: -0.0004

Data Index: 457248 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0548. Min Act: -0.0004

Data Index: 247391 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0513. Min Act: -0.0004

Data Index: 196394 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0503. Min Act: -0.0004

Data Index: 729421 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0519. Min Act: -0.0004

Data Index: 951967 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0510. Min Act: -0.0004

Data Index: 96295 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0473. Min Act: -0.0004

Data Index: 1134274 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0494. Min Act: -0.0004

Data Index: 511708 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0483. Min Act: -0.0004

Data Index: 727118 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0490. Min Act: -0.0004

Data Index: 596043 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0487. Min Act: -0.0004

Data Index: 914118 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0499. Min Act: -0.0004

Data Index: 944002 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0468. Min Act: -0.0004

Data Index: 570992 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0511. Min Act: -0.0004

Data Index: 182006 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0506. Min Act: -0.0004

Data Index: 1114418 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0451. Min Act: -0.0004

Data Index: 1004421 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0485. Min Act: -0.0004

Data Index: 861201 (C4 (Web Text))

Max Activating Token Index: 972