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

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

Neuron 3702 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4597. Min Range: -2.4597

Max Act: 2.4335. Min Act: -0.0000

Data Index: 547908 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 2.4597. Min Range: -2.4597

Max Act: 2.3764. Min Act: -0.0000

Data Index: 927148 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 2.4597. Min Range: -2.4597

Max Act: 2.3581. Min Act: -0.0000

Data Index: 182642 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 2.4597. Min Range: -2.4597

Max Act: 2.4597. Min Act: -0.0000

Data Index: 901106 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 2.4597. Min Range: -2.4597

Max Act: 2.2298. Min Act: -0.0000

Data Index: 180245 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 2.4597. Min Range: -2.4597

Max Act: 1.9686. Min Act: -0.0000

Data Index: 605971 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 2.4597. Min Range: -2.4597

Max Act: 1.9434. Min Act: -0.0000

Data Index: 2722 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 2.4597. Min Range: -2.4597

Max Act: 1.8980. Min Act: -0.0000

Data Index: 1135765 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 2.4597. Min Range: -2.4597

Max Act: 1.8756. Min Act: -0.0000

Data Index: 1197011 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 2.4597. Min Range: -2.4597

Max Act: 1.9769. Min Act: -0.0000

Data Index: 1102547 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 2.4597. Min Range: -2.4597

Max Act: 1.6980. Min Act: -0.0000

Data Index: 596697 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 2.4597. Min Range: -2.4597

Max Act: 1.7760. Min Act: -0.0000

Data Index: 955236 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 2.4597. Min Range: -2.4597

Max Act: 1.7556. Min Act: -0.0000

Data Index: 199537 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 2.4597. Min Range: -2.4597

Max Act: 1.7569. Min Act: -0.0000

Data Index: 1045943 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 2.4597. Min Range: -2.4597

Max Act: 1.6768. Min Act: -0.0000

Data Index: 457034 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 2.4597. Min Range: -2.4597

Max Act: 1.5919. Min Act: -0.0000

Data Index: 699150 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 2.4597. Min Range: -2.4597

Max Act: 1.8753. Min Act: -0.0000

Data Index: 792710 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 2.4597. Min Range: -2.4597

Max Act: 1.6407. Min Act: -0.0000

Data Index: 1267324 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 2.4597. Min Range: -2.4597

Max Act: 1.4581. Min Act: -0.0000

Data Index: 822518 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 2.4597. Min Range: -2.4597

Max Act: 1.7128. Min Act: -0.0000

Data Index: 1312591 (C4 (Web Text))

Max Activating Token Index: 1012