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

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

Neuron 6019 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5557. Min Range: -2.5557

Max Act: 2.5557. Min Act: -0.0000

Data Index: 1113213 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 2.5557. Min Range: -2.5557

Max Act: 2.4008. Min Act: -0.0000

Data Index: 340753 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 2.5557. Min Range: -2.5557

Max Act: 2.3821. Min Act: -0.0001

Data Index: 744768 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 2.5557. Min Range: -2.5557

Max Act: 2.3149. Min Act: -0.0000

Data Index: 321950 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 2.5557. Min Range: -2.5557

Max Act: 2.2741. Min Act: -0.0000

Data Index: 582623 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 2.5557. Min Range: -2.5557

Max Act: 2.1333. Min Act: -0.0000

Data Index: 466203 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 2.5557. Min Range: -2.5557

Max Act: 2.1766. Min Act: -0.0000

Data Index: 795933 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 2.5557. Min Range: -2.5557

Max Act: 2.1516. Min Act: -0.0000

Data Index: 539445 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 2.5557. Min Range: -2.5557

Max Act: 2.2668. Min Act: -0.0000

Data Index: 1503937 (Python Code)

Max Activating Token Index: 250

Text #9

Max Range: 2.5557. Min Range: -2.5557

Max Act: 2.1246. Min Act: -0.0000

Data Index: 755778 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 2.5557. Min Range: -2.5557

Max Act: 2.1272. Min Act: -0.0000

Data Index: 281251 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 2.5557. Min Range: -2.5557

Max Act: 2.1252. Min Act: -0.0000

Data Index: 1549475 (Python Code)

Max Activating Token Index: 981

Text #12

Max Range: 2.5557. Min Range: -2.5557

Max Act: 2.1071. Min Act: -0.0000

Data Index: 53082 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 2.5557. Min Range: -2.5557

Max Act: 2.1118. Min Act: -0.0000

Data Index: 1374493 (Python Code)

Max Activating Token Index: 255

Text #14

Max Range: 2.5557. Min Range: -2.5557

Max Act: 1.9743. Min Act: -0.0000

Data Index: 234165 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 2.5557. Min Range: -2.5557

Max Act: 2.0414. Min Act: -0.0000

Data Index: 576500 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 2.5557. Min Range: -2.5557

Max Act: 1.9349. Min Act: -0.0000

Data Index: 1113244 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 2.5557. Min Range: -2.5557

Max Act: 1.9488. Min Act: -0.0000

Data Index: 1214305 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 2.5557. Min Range: -2.5557

Max Act: 1.9408. Min Act: -0.0000

Data Index: 615994 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 2.5557. Min Range: -2.5557

Max Act: 1.9360. Min Act: -0.0000

Data Index: 937248 (C4 (Web Text))

Max Activating Token Index: 251