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

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

Neuron 4887 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8527. Min Range: -2.8527

Max Act: 2.8527. Min Act: -0.0000

Data Index: 163960 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 2.8527. Min Range: -2.8527

Max Act: 2.2116. Min Act: -0.0000

Data Index: 334851 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 2.8527. Min Range: -2.8527

Max Act: 2.0668. Min Act: -0.0000

Data Index: 278085 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 2.8527. Min Range: -2.8527

Max Act: 1.7978. Min Act: -0.0000

Data Index: 283412 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 2.8527. Min Range: -2.8527

Max Act: 1.8957. Min Act: -0.0000

Data Index: 198219 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 2.8527. Min Range: -2.8527

Max Act: 1.7182. Min Act: -0.0001

Data Index: 741219 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 2.8527. Min Range: -2.8527

Max Act: 1.7897. Min Act: -0.0000

Data Index: 451449 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 2.8527. Min Range: -2.8527

Max Act: 1.7157. Min Act: -0.0000

Data Index: 149514 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 2.8527. Min Range: -2.8527

Max Act: 1.6962. Min Act: -0.0000

Data Index: 631221 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 2.8527. Min Range: -2.8527

Max Act: 1.6913. Min Act: -0.0000

Data Index: 433733 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 2.8527. Min Range: -2.8527

Max Act: 1.6007. Min Act: -0.0000

Data Index: 37934 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 2.8527. Min Range: -2.8527

Max Act: 1.7432. Min Act: -0.0000

Data Index: 812393 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 2.8527. Min Range: -2.8527

Max Act: 1.5545. Min Act: -0.0000

Data Index: 362232 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 2.8527. Min Range: -2.8527

Max Act: 1.5870. Min Act: -0.0000

Data Index: 968936 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 2.8527. Min Range: -2.8527

Max Act: 1.5802. Min Act: -0.0001

Data Index: 487155 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 2.8527. Min Range: -2.8527

Max Act: 1.5847. Min Act: -0.0001

Data Index: 446258 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 2.8527. Min Range: -2.8527

Max Act: 1.5611. Min Act: -0.0001

Data Index: 404902 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 2.8527. Min Range: -2.8527

Max Act: 1.5058. Min Act: -0.0000

Data Index: 367120 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 2.8527. Min Range: -2.8527

Max Act: 1.5047. Min Act: -0.0000

Data Index: 296169 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 2.8527. Min Range: -2.8527

Max Act: 1.5098. Min Act: -0.0000

Data Index: 1226039 (C4 (Web Text))

Max Activating Token Index: 182