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

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

Neuron 3460 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1804. Min Range: -1.1804

Max Act: 1.1429. Min Act: -0.0000

Data Index: 470480 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 1.1804. Min Range: -1.1804

Max Act: 1.1804. Min Act: -0.0001

Data Index: 475429 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 1.1804. Min Range: -1.1804

Max Act: 1.1218. Min Act: -0.0000

Data Index: 671360 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 1.1804. Min Range: -1.1804

Max Act: 1.0727. Min Act: -0.0000

Data Index: 1287667 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 1.1804. Min Range: -1.1804

Max Act: 1.0517. Min Act: -0.0001

Data Index: 1179389 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 1.1804. Min Range: -1.1804

Max Act: 1.0306. Min Act: -0.0001

Data Index: 1211324 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.8722. Min Act: -0.0000

Data Index: 297392 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.8015. Min Act: -0.0000

Data Index: 158149 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.9622. Min Act: -0.0001

Data Index: 375267 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.9254. Min Act: -0.0000

Data Index: 937507 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 1.1804. Min Range: -1.1804

Max Act: 1.0095. Min Act: -0.0001

Data Index: 1079595 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.9069. Min Act: -0.0001

Data Index: 1113512 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.8692. Min Act: -0.0000

Data Index: 648909 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.8640. Min Act: -0.0000

Data Index: 310859 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.8761. Min Act: -0.0000

Data Index: 576015 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.8253. Min Act: -0.0000

Data Index: 1104441 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.8591. Min Act: -0.0001

Data Index: 948614 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.8084. Min Act: -0.0000

Data Index: 1290627 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.8346. Min Act: -0.0000

Data Index: 817486 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.8323. Min Act: -0.0001

Data Index: 871973 (C4 (Web Text))

Max Activating Token Index: 269