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

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

Neuron 3932 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: 0.7686. Min Range: -0.7686

Max Act: 0.7686. Min Act: -0.0000

Data Index: 427254 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.7139. Min Act: -0.0000

Data Index: 827614 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.7105. Min Act: -0.0000

Data Index: 105501 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.7470. Min Act: -0.0000

Data Index: 727276 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.7121. Min Act: -0.0000

Data Index: 1283821 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.6740. Min Act: -0.0000

Data Index: 447652 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.6429. Min Act: -0.0000

Data Index: 489640 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.6221. Min Act: -0.0000

Data Index: 288060 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.6277. Min Act: -0.0000

Data Index: 550911 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.6446. Min Act: -0.0000

Data Index: 776848 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.6043. Min Act: -0.0000

Data Index: 1172110 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1119343 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.5750. Min Act: -0.0000

Data Index: 668049 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.6107. Min Act: -0.0000

Data Index: 78668 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.6035. Min Act: -0.0000

Data Index: 764441 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.6024. Min Act: -0.0000

Data Index: 676524 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.5814. Min Act: -0.0000

Data Index: 1084893 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.5523. Min Act: -0.0000

Data Index: 368987 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.5556. Min Act: -0.0000

Data Index: 911267 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.6303. Min Act: -0.0000

Data Index: 34805 (C4 (Web Text))

Max Activating Token Index: 625