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

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

Neuron 273 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: 0.9368. Min Range: -0.9368

Max Act: 0.9368. Min Act: -0.0000

Data Index: 46134 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.6946. Min Act: -0.0000

Data Index: 655224 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.6372. Min Act: -0.0000

Data Index: 310384 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.5920. Min Act: -0.0000

Data Index: 90633 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.6377. Min Act: -0.0000

Data Index: 313289 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.5788. Min Act: -0.0000

Data Index: 860390 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1292859 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.5926. Min Act: -0.0000

Data Index: 1101673 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.5831. Min Act: -0.0000

Data Index: 200327 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1043955 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.5918. Min Act: -0.0000

Data Index: 625659 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.5956. Min Act: -0.0000

Data Index: 890822 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.5470. Min Act: -0.0000

Data Index: 679620 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.5062. Min Act: -0.0000

Data Index: 500782 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.5595. Min Act: -0.0000

Data Index: 48784 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.5458. Min Act: -0.0000

Data Index: 196012 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.5493. Min Act: -0.0000

Data Index: 1216182 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.4770. Min Act: -0.0000

Data Index: 632188 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.4828. Min Act: -0.0000

Data Index: 759085 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.4871. Min Act: -0.0000

Data Index: 586749 (C4 (Web Text))

Max Activating Token Index: 556