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

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

Neuron 1954 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2616. Min Range: -3.2616

Max Act: 3.2616. Min Act: -0.0002

Data Index: 350900 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.9121. Min Act: -0.0002

Data Index: 938838 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.7247. Min Act: -0.0002

Data Index: 787919 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.3423. Min Act: -0.0002

Data Index: 105861 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.5486. Min Act: -0.0002

Data Index: 515406 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.2974. Min Act: -0.0002

Data Index: 284897 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.5796. Min Act: -0.0001

Data Index: 764579 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.6039. Min Act: -0.0002

Data Index: 454006 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.4466. Min Act: -0.0002

Data Index: 650795 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.7986. Min Act: -0.0002

Data Index: 968820 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.4312. Min Act: -0.0002

Data Index: 844932 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.6707. Min Act: -0.0002

Data Index: 226255 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.4309. Min Act: -0.0002

Data Index: 960636 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.6103. Min Act: -0.0002

Data Index: 520585 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.5189. Min Act: -0.0002

Data Index: 964915 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.5910. Min Act: -0.0002

Data Index: 1346220 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.4488. Min Act: -0.0002

Data Index: 254396 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.3234. Min Act: -0.0001

Data Index: 406627 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.3934. Min Act: -0.0001

Data Index: 559441 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.4054. Min Act: -0.0002

Data Index: 498098 (C4 (Web Text))

Max Activating Token Index: 993