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

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

Neuron 1885 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2988. Min Range: -1.2988

Max Act: 1.2988. Min Act: -0.0001

Data Index: 620555 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 1.2988. Min Range: -1.2988

Max Act: 0.9306. Min Act: -0.0001

Data Index: 344165 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 1.2988. Min Range: -1.2988

Max Act: 1.0063. Min Act: -0.0001

Data Index: 585101 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 1.2988. Min Range: -1.2988

Max Act: 0.9608. Min Act: -0.0001

Data Index: 1520739 (Python Code)

Max Activating Token Index: 716

Text #4

Max Range: 1.2988. Min Range: -1.2988

Max Act: 0.9763. Min Act: -0.0001

Data Index: 720460 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 1.2988. Min Range: -1.2988

Max Act: 0.9465. Min Act: -0.0001

Data Index: 1117568 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 1.2988. Min Range: -1.2988

Max Act: 0.9230. Min Act: -0.0001

Data Index: 106906 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 1.2988. Min Range: -1.2988

Max Act: 0.9069. Min Act: -0.0001

Data Index: 189342 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 1.2988. Min Range: -1.2988

Max Act: 0.8627. Min Act: -0.0001

Data Index: 1106132 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 1.2988. Min Range: -1.2988

Max Act: 0.8871. Min Act: -0.0001

Data Index: 363827 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 1.2988. Min Range: -1.2988

Max Act: 0.8128. Min Act: -0.0001

Data Index: 1148717 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 1.2988. Min Range: -1.2988

Max Act: 0.9175. Min Act: -0.0001

Data Index: 1303381 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 1.2988. Min Range: -1.2988

Max Act: 0.9366. Min Act: -0.0001

Data Index: 716698 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 1.2988. Min Range: -1.2988

Max Act: 0.8808. Min Act: -0.0001

Data Index: 246268 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 1.2988. Min Range: -1.2988

Max Act: 0.8757. Min Act: -0.0001

Data Index: 1321401 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 1.2988. Min Range: -1.2988

Max Act: 0.8677. Min Act: -0.0001

Data Index: 349066 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 1.2988. Min Range: -1.2988

Max Act: 0.8418. Min Act: -0.0001

Data Index: 364592 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 1.2988. Min Range: -1.2988

Max Act: 0.8807. Min Act: -0.0001

Data Index: 1122041 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 1.2988. Min Range: -1.2988

Max Act: 0.7993. Min Act: -0.0001

Data Index: 1571961 (Python Code)

Max Activating Token Index: 730

Text #19

Max Range: 1.2988. Min Range: -1.2988

Max Act: 0.8494. Min Act: -0.0001

Data Index: 1394371 (Python Code)

Max Activating Token Index: 735