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

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

Neuron 2141 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.4812. Min Act: -0.0001

Data Index: 1341198 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.8391. Min Act: -0.0001

Data Index: 438609 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.7745. Min Act: -0.0001

Data Index: 650601 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.7528. Min Act: -0.0001

Data Index: 464376 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.7261. Min Act: -0.0001

Data Index: 706317 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.6617. Min Act: -0.0001

Data Index: 223932 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.6693. Min Act: -0.0001

Data Index: 849699 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.6341. Min Act: -0.0001

Data Index: 689504 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.7044. Min Act: -0.0001

Data Index: 209460 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.6495. Min Act: -0.0001

Data Index: 125825 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.6487. Min Act: -0.0001

Data Index: 366269 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.6429. Min Act: -0.0001

Data Index: 326698 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.6313. Min Act: -0.0000

Data Index: 952471 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.6989. Min Act: -0.0001

Data Index: 65670 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.6181. Min Act: -0.0001

Data Index: 545240 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.5987. Min Act: -0.0001

Data Index: 572879 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.5705. Min Act: -0.0000

Data Index: 932036 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.6512. Min Act: -0.0000

Data Index: 779673 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.6727. Min Act: -0.0001

Data Index: 1104625 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 1.4812. Min Range: -1.4812

Max Act: 0.6888. Min Act: -0.0001

Data Index: 12471 (C4 (Web Text))

Max Activating Token Index: 114