Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4148 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.5125. Min Range: -5.5125

Max Act: 5.5125. Min Act: -0.0000

Data Index: 688109 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 5.5125. Min Range: -5.5125

Max Act: 4.6388. Min Act: -0.0000

Data Index: 1100282 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 5.5125. Min Range: -5.5125

Max Act: 4.5010. Min Act: -0.0000

Data Index: 207868 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 5.5125. Min Range: -5.5125

Max Act: 4.3672. Min Act: -0.0000

Data Index: 400629 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 5.5125. Min Range: -5.5125

Max Act: 4.1574. Min Act: -0.0000

Data Index: 447089 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 5.5125. Min Range: -5.5125

Max Act: 4.4350. Min Act: -0.0000

Data Index: 856442 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 5.5125. Min Range: -5.5125

Max Act: 4.0074. Min Act: -0.0000

Data Index: 632685 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 5.5125. Min Range: -5.5125

Max Act: 3.7717. Min Act: -0.0000

Data Index: 972348 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 5.5125. Min Range: -5.5125

Max Act: 4.1705. Min Act: -0.0000

Data Index: 740619 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 5.5125. Min Range: -5.5125

Max Act: 3.8742. Min Act: -0.0000

Data Index: 1293851 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 5.5125. Min Range: -5.5125

Max Act: 3.6725. Min Act: -0.0000

Data Index: 1057220 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 5.5125. Min Range: -5.5125

Max Act: 3.8256. Min Act: -0.0000

Data Index: 96139 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 5.5125. Min Range: -5.5125

Max Act: 3.4775. Min Act: -0.0000

Data Index: 467266 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 5.5125. Min Range: -5.5125

Max Act: 3.6603. Min Act: -0.0000

Data Index: 5482 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 5.5125. Min Range: -5.5125

Max Act: 3.1909. Min Act: -0.0000

Data Index: 1434226 (Python Code)

Max Activating Token Index: 303

Text #15

Max Range: 5.5125. Min Range: -5.5125

Max Act: 3.3670. Min Act: -0.0000

Data Index: 802377 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 5.5125. Min Range: -5.5125

Max Act: 2.7810. Min Act: -0.0000

Data Index: 762539 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 5.5125. Min Range: -5.5125

Max Act: 2.5936. Min Act: -0.0000

Data Index: 217880 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 5.5125. Min Range: -5.5125

Max Act: 2.5623. Min Act: -0.0000

Data Index: 83577 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 5.5125. Min Range: -5.5125

Max Act: 3.0938. Min Act: -0.0000

Data Index: 887770 (C4 (Web Text))

Max Activating Token Index: 107