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

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

Neuron 3275 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: 3.1100. Min Range: -3.1100

Max Act: 3.1061. Min Act: -0.0000

Data Index: 11347 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 3.1100. Min Range: -3.1100

Max Act: 3.0703. Min Act: -0.0001

Data Index: 659031 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.9693. Min Act: -0.0000

Data Index: 1157505 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.8688. Min Act: -0.0001

Data Index: 1347222 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 3.1100. Min Range: -3.1100

Max Act: 3.1100. Min Act: -0.0001

Data Index: 718456 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.5755. Min Act: -0.0000

Data Index: 1155578 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.8823. Min Act: -0.0001

Data Index: 367455 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.5387. Min Act: -0.0001

Data Index: 37441 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.5826. Min Act: -0.0001

Data Index: 21918 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.4208. Min Act: -0.0001

Data Index: 395327 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.2982. Min Act: -0.0000

Data Index: 1222495 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.2523. Min Act: -0.0000

Data Index: 1280202 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.0233. Min Act: -0.0001

Data Index: 907259 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.2282. Min Act: -0.0001

Data Index: 678122 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.3667. Min Act: -0.0001

Data Index: 265173 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.2186. Min Act: -0.0001

Data Index: 626870 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.3234. Min Act: -0.0001

Data Index: 1120719 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.0659. Min Act: -0.0001

Data Index: 136855 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.1363. Min Act: -0.0001

Data Index: 1060380 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 3.1100. Min Range: -3.1100

Max Act: 2.1272. Min Act: -0.0001

Data Index: 80827 (C4 (Web Text))

Max Activating Token Index: 7