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

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

Neuron 4451 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3484. Min Range: -6.3484

Max Act: 6.3165. Min Act: -0.0000

Data Index: 374766 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 6.3484. Min Range: -6.3484

Max Act: 6.3484. Min Act: -0.0000

Data Index: 791595 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 6.3484. Min Range: -6.3484

Max Act: 6.2440. Min Act: -0.0000

Data Index: 1045289 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 6.3484. Min Range: -6.3484

Max Act: 6.0592. Min Act: -0.0000

Data Index: 327937 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 6.3484. Min Range: -6.3484

Max Act: 5.8303. Min Act: -0.0000

Data Index: 1166221 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 6.3484. Min Range: -6.3484

Max Act: 6.0152. Min Act: -0.0000

Data Index: 687468 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 6.3484. Min Range: -6.3484

Max Act: 6.1876. Min Act: -0.0000

Data Index: 737594 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 6.3484. Min Range: -6.3484

Max Act: 5.7045. Min Act: -0.0000

Data Index: 221694 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 6.3484. Min Range: -6.3484

Max Act: 5.8576. Min Act: -0.0000

Data Index: 1138901 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 6.3484. Min Range: -6.3484

Max Act: 5.7327. Min Act: 0.0000

Data Index: 866307 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 6.3484. Min Range: -6.3484

Max Act: 5.2149. Min Act: -0.0000

Data Index: 554995 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 6.3484. Min Range: -6.3484

Max Act: 3.9512. Min Act: -0.0000

Data Index: 134672 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 6.3484. Min Range: -6.3484

Max Act: 3.8767. Min Act: -0.0000

Data Index: 635518 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 6.3484. Min Range: -6.3484

Max Act: 2.8788. Min Act: -0.0001

Data Index: 536501 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 6.3484. Min Range: -6.3484

Max Act: 2.7065. Min Act: -0.0000

Data Index: 883836 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 6.3484. Min Range: -6.3484

Max Act: 2.6930. Min Act: -0.0000

Data Index: 818376 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 6.3484. Min Range: -6.3484

Max Act: 2.3892. Min Act: -0.0000

Data Index: 1053116 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 6.3484. Min Range: -6.3484

Max Act: 2.3543. Min Act: -0.0000

Data Index: 318713 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 6.3484. Min Range: -6.3484

Max Act: 2.3057. Min Act: 0.0000

Data Index: 248667 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 6.3484. Min Range: -6.3484

Max Act: 2.2976. Min Act: -0.0000

Data Index: 1071059 (C4 (Web Text))

Max Activating Token Index: 26