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

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

Neuron 3802 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.5312. Min Act: -0.0000

Data Index: 313787 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1135450 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4573. Min Act: -0.0000

Data Index: 322869 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4775. Min Act: -0.0000

Data Index: 912396 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.5052. Min Act: -0.0000

Data Index: 828139 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1162227 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.5045. Min Act: -0.0000

Data Index: 1098602 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4864. Min Act: -0.0000

Data Index: 67073 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4552. Min Act: -0.0000

Data Index: 972689 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4645. Min Act: -0.0000

Data Index: 367394 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4761. Min Act: -0.0000

Data Index: 1061618 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.5121. Min Act: -0.0000

Data Index: 1324913 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4862. Min Act: -0.0000

Data Index: 569373 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4488. Min Act: -0.0000

Data Index: 105817 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4383. Min Act: -0.0000

Data Index: 495789 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4640. Min Act: -0.0000

Data Index: 326732 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4410. Min Act: -0.0000

Data Index: 1176301 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4754. Min Act: -0.0000

Data Index: 655411 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4112. Min Act: -0.0000

Data Index: 293546 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4784. Min Act: -0.0000

Data Index: 917852 (C4 (Web Text))

Max Activating Token Index: 888