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

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

Neuron 5909 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8059. Min Range: -2.8059

Max Act: 2.8059. Min Act: -0.0000

Data Index: 860588 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 2.8059. Min Range: -2.8059

Max Act: 2.4381. Min Act: -0.0000

Data Index: 652540 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 2.8059. Min Range: -2.8059

Max Act: 2.4085. Min Act: -0.0000

Data Index: 697022 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 2.8059. Min Range: -2.8059

Max Act: 2.3928. Min Act: -0.0000

Data Index: 1324750 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 2.8059. Min Range: -2.8059

Max Act: 2.2363. Min Act: -0.0000

Data Index: 1324182 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 2.8059. Min Range: -2.8059

Max Act: 1.9767. Min Act: -0.0000

Data Index: 7678 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 2.8059. Min Range: -2.8059

Max Act: 1.9113. Min Act: -0.0000

Data Index: 471783 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 2.8059. Min Range: -2.8059

Max Act: 1.9321. Min Act: -0.0000

Data Index: 611492 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 2.8059. Min Range: -2.8059

Max Act: 1.9164. Min Act: -0.0000

Data Index: 889382 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 2.8059. Min Range: -2.8059

Max Act: 2.1110. Min Act: -0.0000

Data Index: 629624 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 2.8059. Min Range: -2.8059

Max Act: 2.1020. Min Act: -0.0000

Data Index: 221242 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 2.8059. Min Range: -2.8059

Max Act: 2.0088. Min Act: -0.0000

Data Index: 783582 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 2.8059. Min Range: -2.8059

Max Act: 1.9622. Min Act: -0.0000

Data Index: 1179931 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 2.8059. Min Range: -2.8059

Max Act: 1.9162. Min Act: -0.0000

Data Index: 806553 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 2.8059. Min Range: -2.8059

Max Act: 2.0187. Min Act: -0.0000

Data Index: 622866 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 2.8059. Min Range: -2.8059

Max Act: 1.9109. Min Act: -0.0000

Data Index: 1022183 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 2.8059. Min Range: -2.8059

Max Act: 1.9190. Min Act: -0.0000

Data Index: 4249 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 2.8059. Min Range: -2.8059

Max Act: 1.8919. Min Act: -0.0000

Data Index: 330346 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 2.8059. Min Range: -2.8059

Max Act: 1.8988. Min Act: -0.0000

Data Index: 576388 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 2.8059. Min Range: -2.8059

Max Act: 2.0197. Min Act: -0.0000

Data Index: 785667 (C4 (Web Text))

Max Activating Token Index: 294