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

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

Neuron 1290 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: 2.6680. Min Range: -2.6680

Max Act: 2.5332. Min Act: -0.0000

Data Index: 1158612 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 2.6680. Min Range: -2.6680

Max Act: 2.6680. Min Act: -0.0000

Data Index: 1327517 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 2.6680. Min Range: -2.6680

Max Act: 2.2732. Min Act: -0.0000

Data Index: 717034 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 2.6680. Min Range: -2.6680

Max Act: 2.2798. Min Act: -0.0000

Data Index: 587926 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 2.6680. Min Range: -2.6680

Max Act: 1.8549. Min Act: -0.0000

Data Index: 359371 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 2.6680. Min Range: -2.6680

Max Act: 1.7086. Min Act: -0.0000

Data Index: 709510 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 2.6680. Min Range: -2.6680

Max Act: 1.7545. Min Act: -0.0000

Data Index: 63751 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 2.6680. Min Range: -2.6680

Max Act: 1.7363. Min Act: -0.0000

Data Index: 1114777 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 2.6680. Min Range: -2.6680

Max Act: 1.7516. Min Act: -0.0000

Data Index: 1213820 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 2.6680. Min Range: -2.6680

Max Act: 1.5918. Min Act: -0.0000

Data Index: 1289475 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 2.6680. Min Range: -2.6680

Max Act: 1.6979. Min Act: -0.0000

Data Index: 72199 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 2.6680. Min Range: -2.6680

Max Act: 1.6611. Min Act: -0.0000

Data Index: 321002 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 2.6680. Min Range: -2.6680

Max Act: 1.7581. Min Act: -0.0000

Data Index: 963705 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 2.6680. Min Range: -2.6680

Max Act: 1.7416. Min Act: -0.0000

Data Index: 207203 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 2.6680. Min Range: -2.6680

Max Act: 1.7708. Min Act: -0.0000

Data Index: 630459 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 2.6680. Min Range: -2.6680

Max Act: 1.6911. Min Act: -0.0000

Data Index: 886701 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 2.6680. Min Range: -2.6680

Max Act: 1.6211. Min Act: -0.0000

Data Index: 864473 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 2.6680. Min Range: -2.6680

Max Act: 1.6059. Min Act: -0.0000

Data Index: 74336 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 2.6680. Min Range: -2.6680

Max Act: 1.6192. Min Act: -0.0000

Data Index: 1331353 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 2.6680. Min Range: -2.6680

Max Act: 1.6416. Min Act: -0.0000

Data Index: 425167 (C4 (Web Text))

Max Activating Token Index: 756