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

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

Neuron 792 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5622. Min Range: -0.5622

Max Act: 0.5270. Min Act: -0.0001

Data Index: 807395 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.5622. Min Range: -0.5622

Max Act: 0.5369. Min Act: -0.0001

Data Index: 362647 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.5622. Min Range: -0.5622

Max Act: 0.5622. Min Act: -0.0001

Data Index: 1150006 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.5622. Min Range: -0.5622

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1352922 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 0.5622. Min Range: -0.5622

Max Act: 0.4687. Min Act: -0.0001

Data Index: 1240931 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.5622. Min Range: -0.5622

Max Act: 0.5051. Min Act: -0.0001

Data Index: 644022 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.5622. Min Range: -0.5622

Max Act: 0.4618. Min Act: -0.0001

Data Index: 354090 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 0.5622. Min Range: -0.5622

Max Act: 0.4606. Min Act: -0.0001

Data Index: 90103 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.5622. Min Range: -0.5622

Max Act: 0.4458. Min Act: -0.0001

Data Index: 264169 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 0.5622. Min Range: -0.5622

Max Act: 0.5116. Min Act: -0.0001

Data Index: 212744 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.5622. Min Range: -0.5622

Max Act: 0.4644. Min Act: -0.0001

Data Index: 995250 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.5622. Min Range: -0.5622

Max Act: 0.4739. Min Act: -0.0001

Data Index: 422048 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.5622. Min Range: -0.5622

Max Act: 0.3727. Min Act: -0.0001

Data Index: 130944 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 0.5622. Min Range: -0.5622

Max Act: 0.4180. Min Act: -0.0001

Data Index: 388299 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.5622. Min Range: -0.5622

Max Act: 0.4264. Min Act: -0.0001

Data Index: 135721 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.5622. Min Range: -0.5622

Max Act: 0.4080. Min Act: -0.0001

Data Index: 1217903 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.5622. Min Range: -0.5622

Max Act: 0.4315. Min Act: -0.0001

Data Index: 47677 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.5622. Min Range: -0.5622

Max Act: 0.4048. Min Act: -0.0001

Data Index: 17321 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.5622. Min Range: -0.5622

Max Act: 0.4157. Min Act: -0.0001

Data Index: 1012437 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 0.5622. Min Range: -0.5622

Max Act: 0.4139. Min Act: -0.0001

Data Index: 242338 (C4 (Web Text))

Max Activating Token Index: 937