Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1697 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.7313. Min Act: -0.0005

Data Index: 1007311 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.7613. Min Act: -0.0005

Data Index: 603610 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.7756. Min Act: -0.0005

Data Index: 140755 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.7340. Min Act: -0.0005

Data Index: 428477 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.7090. Min Act: -0.0005

Data Index: 869964 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.7006. Min Act: -0.0005

Data Index: 297173 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6897. Min Act: -0.0005

Data Index: 995536 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6309. Min Act: -0.0005

Data Index: 216180 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6361. Min Act: -0.0005

Data Index: 516259 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6567. Min Act: -0.0005

Data Index: 551041 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6226. Min Act: -0.0005

Data Index: 694115 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6587. Min Act: -0.0005

Data Index: 546104 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6070. Min Act: -0.0005

Data Index: 521578 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6116. Min Act: -0.0005

Data Index: 842465 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.5903. Min Act: -0.0005

Data Index: 566454 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6284. Min Act: -0.0005

Data Index: 1211563 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6252. Min Act: -0.0005

Data Index: 763263 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6226. Min Act: -0.0005

Data Index: 733185 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6059. Min Act: -0.0005

Data Index: 431271 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6376. Min Act: -0.0005

Data Index: 340911 (C4 (Web Text))

Max Activating Token Index: 354