Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3899 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6908. Min Act: -0.0000

Data Index: 140710 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6813. Min Act: -0.0000

Data Index: 748807 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.7450. Min Act: -0.0000

Data Index: 582973 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6942. Min Act: -0.0000

Data Index: 1136057 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6288. Min Act: -0.0000

Data Index: 1291283 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6273. Min Act: -0.0000

Data Index: 752170 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6087. Min Act: -0.0000

Data Index: 50753 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.6275. Min Act: -0.0000

Data Index: 333936 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1337957 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.5688. Min Act: -0.0000

Data Index: 683761 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.5843. Min Act: -0.0000

Data Index: 848622 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.5734. Min Act: -0.0000

Data Index: 404903 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.5383. Min Act: -0.0000

Data Index: 1182839 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.5335. Min Act: -0.0000

Data Index: 289845 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.5650. Min Act: -0.0000

Data Index: 474664 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.5528. Min Act: -0.0000

Data Index: 986973 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.5320. Min Act: -0.0000

Data Index: 1193987 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.5305. Min Act: -0.0000

Data Index: 145721 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1179314 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.7450. Min Range: -0.7450

Max Act: 0.5201. Min Act: -0.0000

Data Index: 696166 (C4 (Web Text))

Max Activating Token Index: 237