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

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

Neuron 3383 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4510. Min Range: -3.4510

Max Act: 3.4510. Min Act: -0.0000

Data Index: 73549 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 3.4510. Min Range: -3.4510

Max Act: 3.4202. Min Act: -0.0000

Data Index: 29636 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 3.4510. Min Range: -3.4510

Max Act: 3.0062. Min Act: -0.0000

Data Index: 237823 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 3.4510. Min Range: -3.4510

Max Act: 2.8519. Min Act: -0.0000

Data Index: 1341818 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 3.4510. Min Range: -3.4510

Max Act: 2.8187. Min Act: -0.0000

Data Index: 1348090 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 3.4510. Min Range: -3.4510

Max Act: 3.0962. Min Act: -0.0000

Data Index: 1223812 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 3.4510. Min Range: -3.4510

Max Act: 2.8837. Min Act: -0.0000

Data Index: 82119 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 3.4510. Min Range: -3.4510

Max Act: 2.7488. Min Act: -0.0000

Data Index: 38539 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 3.4510. Min Range: -3.4510

Max Act: 2.7162. Min Act: -0.0000

Data Index: 61069 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 3.4510. Min Range: -3.4510

Max Act: 2.5788. Min Act: -0.0000

Data Index: 167640 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 3.4510. Min Range: -3.4510

Max Act: 2.6792. Min Act: -0.0000

Data Index: 173875 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 3.4510. Min Range: -3.4510

Max Act: 2.7985. Min Act: -0.0000

Data Index: 48966 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 3.4510. Min Range: -3.4510

Max Act: 2.6794. Min Act: -0.0000

Data Index: 1092729 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 3.4510. Min Range: -3.4510

Max Act: 2.7951. Min Act: -0.0000

Data Index: 790933 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 3.4510. Min Range: -3.4510

Max Act: 2.6444. Min Act: -0.0000

Data Index: 1108234 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 3.4510. Min Range: -3.4510

Max Act: 2.6281. Min Act: -0.0000

Data Index: 186011 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 3.4510. Min Range: -3.4510

Max Act: 2.4597. Min Act: -0.0000

Data Index: 720479 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 3.4510. Min Range: -3.4510

Max Act: 2.4574. Min Act: -0.0000

Data Index: 247915 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 3.4510. Min Range: -3.4510

Max Act: 2.5803. Min Act: -0.0000

Data Index: 125002 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 3.4510. Min Range: -3.4510

Max Act: 2.5889. Min Act: -0.0000

Data Index: 834184 (C4 (Web Text))

Max Activating Token Index: 271