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

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

Neuron 1039 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: 0.7204. Min Range: -0.7204

Max Act: 0.7204. Min Act: -0.0000

Data Index: 1465668 (Python Code)

Max Activating Token Index: 765

Text #1

Max Range: 0.7204. Min Range: -0.7204

Max Act: 0.4842. Min Act: -0.0000

Data Index: 254001 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.7204. Min Range: -0.7204

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1453094 (Python Code)

Max Activating Token Index: 742

Text #3

Max Range: 0.7204. Min Range: -0.7204

Max Act: 0.4989. Min Act: -0.0000

Data Index: 723977 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.7204. Min Range: -0.7204

Max Act: 0.4147. Min Act: 0.0000

Data Index: 570111 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.7204. Min Range: -0.7204

Max Act: 0.3503. Min Act: -0.0000

Data Index: 599174 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 0.7204. Min Range: -0.7204

Max Act: 0.3921. Min Act: -0.0000

Data Index: 1503691 (Python Code)

Max Activating Token Index: 952

Text #7

Max Range: 0.7204. Min Range: -0.7204

Max Act: 0.3513. Min Act: -0.0000

Data Index: 812041 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.7204. Min Range: -0.7204

Max Act: 0.3498. Min Act: -0.0000

Data Index: 811361 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.7204. Min Range: -0.7204

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1388609 (Python Code)

Max Activating Token Index: 932

Text #10

Max Range: 0.7204. Min Range: -0.7204

Max Act: 0.3529. Min Act: -0.0000

Data Index: 1415239 (Python Code)

Max Activating Token Index: 983

Text #11

Max Range: 0.7204. Min Range: -0.7204

Max Act: 0.3453. Min Act: -0.0000

Data Index: 28907 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 0.7204. Min Range: -0.7204

Max Act: 0.3414. Min Act: -0.0000

Data Index: 1350143 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.7204. Min Range: -0.7204

Max Act: 0.3488. Min Act: -0.0000

Data Index: 1120972 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.7204. Min Range: -0.7204

Max Act: 0.3115. Min Act: -0.0000

Data Index: 1184790 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.7204. Min Range: -0.7204

Max Act: 0.3159. Min Act: -0.0000

Data Index: 140651 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 0.7204. Min Range: -0.7204

Max Act: 0.3053. Min Act: -0.0000

Data Index: 1312347 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.7204. Min Range: -0.7204

Max Act: 0.3275. Min Act: -0.0000

Data Index: 554490 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.7204. Min Range: -0.7204

Max Act: 0.3181. Min Act: -0.0000

Data Index: 497127 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.7204. Min Range: -0.7204

Max Act: 0.3302. Min Act: -0.0000

Data Index: 474938 (C4 (Web Text))

Max Activating Token Index: 114