Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4585 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.9106. Min Act: -0.0000

Data Index: 1330140 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.7755. Min Act: -0.0000

Data Index: 519700 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.7411. Min Act: -0.0000

Data Index: 520365 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.7605. Min Act: -0.0000

Data Index: 436023 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.8521. Min Act: -0.0000

Data Index: 314350 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.8206. Min Act: -0.0000

Data Index: 779447 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.8038. Min Act: -0.0000

Data Index: 884267 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.7845. Min Act: -0.0000

Data Index: 124723 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.8174. Min Act: -0.0000

Data Index: 476760 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.7792. Min Act: -0.0000

Data Index: 251555 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.6775. Min Act: -0.0000

Data Index: 1118866 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.7000. Min Act: -0.0000

Data Index: 1181023 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1153723 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.6592. Min Act: -0.0000

Data Index: 627219 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.6245. Min Act: -0.0000

Data Index: 503468 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.5966. Min Act: -0.0000

Data Index: 616410 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.6590. Min Act: -0.0000

Data Index: 397203 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.6129. Min Act: -0.0000

Data Index: 1010858 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.6339. Min Act: -0.0000

Data Index: 439030 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 0.9106. Min Range: -0.9106

Max Act: 0.5970. Min Act: -0.0000

Data Index: 708051 (C4 (Web Text))

Max Activating Token Index: 679