Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3911 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.7878. Min Act: -0.0000

Data Index: 1144787 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.8091. Min Act: -0.0000

Data Index: 1110619 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.7704. Min Act: -0.0000

Data Index: 396383 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6831. Min Act: -0.0000

Data Index: 73667 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.7057. Min Act: -0.0000

Data Index: 413910 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6243. Min Act: -0.0000

Data Index: 882560 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6390. Min Act: -0.0000

Data Index: 1195516 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1335802 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6181. Min Act: -0.0000

Data Index: 179048 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.5543. Min Act: -0.0000

Data Index: 1037640 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1345214 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6049. Min Act: -0.0000

Data Index: 24733 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.5984. Min Act: -0.0001

Data Index: 762961 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6026. Min Act: -0.0001

Data Index: 698319 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6037. Min Act: -0.0000

Data Index: 663053 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.5844. Min Act: -0.0000

Data Index: 466600 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.5857. Min Act: -0.0000

Data Index: 177795 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.5661. Min Act: -0.0000

Data Index: 627763 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.5781. Min Act: -0.0001

Data Index: 1586193 (Python Code)

Max Activating Token Index: 746

Text #19

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.5563. Min Act: -0.0000

Data Index: 859111 (C4 (Web Text))

Max Activating Token Index: 688