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

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

Neuron 2699 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0229. Min Range: -1.0229

Max Act: 1.0229. Min Act: -0.0000

Data Index: 951274 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.9876. Min Act: -0.0000

Data Index: 554487 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.9299. Min Act: -0.0000

Data Index: 591340 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.8259. Min Act: -0.0000

Data Index: 347986 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1564962 (Python Code)

Max Activating Token Index: 291

Text #5

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.7710. Min Act: -0.0000

Data Index: 586269 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.7605. Min Act: -0.0000

Data Index: 845558 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.7943. Min Act: -0.0000

Data Index: 202015 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.7676. Min Act: -0.0000

Data Index: 438517 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.7528. Min Act: -0.0000

Data Index: 949391 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.7495. Min Act: -0.0000

Data Index: 574634 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.7233. Min Act: -0.0000

Data Index: 521893 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.6938. Min Act: -0.0000

Data Index: 1388200 (Python Code)

Max Activating Token Index: 799

Text #13

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.7074. Min Act: -0.0000

Data Index: 1323139 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.6593. Min Act: -0.0000

Data Index: 553529 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.7029. Min Act: -0.0000

Data Index: 591725 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.7008. Min Act: -0.0000

Data Index: 814281 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.6640. Min Act: -0.0000

Data Index: 802793 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.6761. Min Act: -0.0000

Data Index: 1172315 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.6240. Min Act: -0.0000

Data Index: 732089 (C4 (Web Text))

Max Activating Token Index: 798