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

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

Neuron 5077 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.7299. Min Act: -0.0000

Data Index: 778962 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.6511. Min Act: -0.0001

Data Index: 147367 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.6738. Min Act: -0.0001

Data Index: 1291574 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.6498. Min Act: -0.0000

Data Index: 1162429 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.6542. Min Act: -0.0000

Data Index: 65746 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5815. Min Act: -0.0000

Data Index: 14242 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5933. Min Act: -0.0000

Data Index: 826372 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5791. Min Act: -0.0001

Data Index: 649044 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5796. Min Act: -0.0000

Data Index: 585840 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5698. Min Act: -0.0000

Data Index: 600705 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5346. Min Act: -0.0001

Data Index: 564873 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1209315 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5294. Min Act: -0.0000

Data Index: 3715 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5376. Min Act: -0.0000

Data Index: 425627 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.4896. Min Act: -0.0000

Data Index: 542626 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5201. Min Act: -0.0001

Data Index: 994308 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.4874. Min Act: -0.0000

Data Index: 752707 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5192. Min Act: -0.0000

Data Index: 658091 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5011. Min Act: -0.0000

Data Index: 1108284 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.5003. Min Act: -0.0000

Data Index: 1123728 (C4 (Web Text))

Max Activating Token Index: 214