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

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

Neuron 2967 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: 0.5933. Min Range: -0.5933

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1177884 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.5933. Min Range: -0.5933

Max Act: 0.5025. Min Act: -0.0000

Data Index: 707362 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.5933. Min Range: -0.5933

Max Act: 0.4425. Min Act: -0.0000

Data Index: 395872 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 0.5933. Min Range: -0.5933

Max Act: 0.5933. Min Act: -0.0000

Data Index: 750293 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.5933. Min Range: -0.5933

Max Act: 0.4598. Min Act: -0.0000

Data Index: 1653180 (Python Code)

Max Activating Token Index: 855

Text #5

Max Range: 0.5933. Min Range: -0.5933

Max Act: 0.4824. Min Act: -0.0000

Data Index: 264640 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.5933. Min Range: -0.5933

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1358106 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 0.5933. Min Range: -0.5933

Max Act: 0.4316. Min Act: -0.0000

Data Index: 32590 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.5933. Min Range: -0.5933

Max Act: 0.4241. Min Act: -0.0000

Data Index: 1561095 (Python Code)

Max Activating Token Index: 821

Text #9

Max Range: 0.5933. Min Range: -0.5933

Max Act: 0.4339. Min Act: -0.0000

Data Index: 1321238 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 0.5933. Min Range: -0.5933

Max Act: 0.4127. Min Act: -0.0000

Data Index: 1485386 (Python Code)

Max Activating Token Index: 717

Text #11

Max Range: 0.5933. Min Range: -0.5933

Max Act: 0.4006. Min Act: -0.0000

Data Index: 875524 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 0.5933. Min Range: -0.5933

Max Act: 0.4208. Min Act: -0.0000

Data Index: 92852 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.5933. Min Range: -0.5933

Max Act: 0.3445. Min Act: -0.0000

Data Index: 1196767 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.5933. Min Range: -0.5933

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1415662 (Python Code)

Max Activating Token Index: 877

Text #15

Max Range: 0.5933. Min Range: -0.5933

Max Act: 0.3741. Min Act: -0.0000

Data Index: 738542 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.5933. Min Range: -0.5933

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1162544 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.5933. Min Range: -0.5933

Max Act: 0.3844. Min Act: -0.0000

Data Index: 1183123 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.5933. Min Range: -0.5933

Max Act: 0.4148. Min Act: -0.0000

Data Index: 1412110 (Python Code)

Max Activating Token Index: 437

Text #19

Max Range: 0.5933. Min Range: -0.5933

Max Act: 0.3714. Min Act: -0.0000

Data Index: 306284 (C4 (Web Text))

Max Activating Token Index: 504