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

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

Neuron 2679 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.7652. Min Act: -0.0002

Data Index: 33688 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.7325. Min Act: -0.0001

Data Index: 185691 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.7324. Min Act: -0.0001

Data Index: 585414 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6906. Min Act: -0.0001

Data Index: 215452 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6823. Min Act: -0.0001

Data Index: 870545 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.7109. Min Act: -0.0001

Data Index: 459307 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.5784. Min Act: -0.0001

Data Index: 71301 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6321. Min Act: -0.0001

Data Index: 1052982 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6712. Min Act: -0.0001

Data Index: 48913 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6398. Min Act: -0.0001

Data Index: 628768 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6567. Min Act: -0.0002

Data Index: 1239524 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6763. Min Act: -0.0001

Data Index: 1271810 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6106. Min Act: -0.0001

Data Index: 1077250 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.5821. Min Act: -0.0001

Data Index: 146359 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6430. Min Act: -0.0001

Data Index: 449618 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.5620. Min Act: -0.0002

Data Index: 1192855 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6100. Min Act: -0.0001

Data Index: 873487 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.5810. Min Act: -0.0001

Data Index: 38538 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.5725. Min Act: -0.0001

Data Index: 1030839 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.5455. Min Act: -0.0002

Data Index: 291979 (C4 (Web Text))

Max Activating Token Index: 510