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

Dataset: The Pile

Neuron 707 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1112676 (The Pile)

Max Activating Token Index: 622

Text #1

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.8151. Min Act: -0.0000

Data Index: 982259 (The Pile)

Max Activating Token Index: 709

Text #2

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7996. Min Act: -0.0000

Data Index: 1826850 (The Pile)

Max Activating Token Index: 75

Text #3

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.8082. Min Act: -0.0000

Data Index: 387449 (The Pile)

Max Activating Token Index: 530

Text #4

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7779. Min Act: -0.0000

Data Index: 1114162 (The Pile)

Max Activating Token Index: 843

Text #5

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7809. Min Act: -0.0000

Data Index: 837024 (The Pile)

Max Activating Token Index: 286

Text #6

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7990. Min Act: -0.0000

Data Index: 243545 (The Pile)

Max Activating Token Index: 494

Text #7

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7731. Min Act: -0.0000

Data Index: 1621879 (The Pile)

Max Activating Token Index: 754

Text #8

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7455. Min Act: -0.0000

Data Index: 664642 (The Pile)

Max Activating Token Index: 505

Text #9

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7451. Min Act: -0.0000

Data Index: 1048296 (The Pile)

Max Activating Token Index: 201

Text #10

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7594. Min Act: -0.0000

Data Index: 1937878 (The Pile)

Max Activating Token Index: 625

Text #11

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6934. Min Act: -0.0000

Data Index: 1258059 (The Pile)

Max Activating Token Index: 235

Text #12

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7401. Min Act: -0.0000

Data Index: 1196198 (The Pile)

Max Activating Token Index: 286

Text #13

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7304. Min Act: -0.0000

Data Index: 236101 (The Pile)

Max Activating Token Index: 169

Text #14

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7308. Min Act: -0.0000

Data Index: 399880 (The Pile)

Max Activating Token Index: 351

Text #15

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7525. Min Act: -0.0000

Data Index: 821916 (The Pile)

Max Activating Token Index: 229

Text #16

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7275. Min Act: -0.0000

Data Index: 1302188 (The Pile)

Max Activating Token Index: 519

Text #17

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7089. Min Act: -0.0000

Data Index: 1434846 (The Pile)

Max Activating Token Index: 761

Text #18

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7066. Min Act: -0.0000

Data Index: 1401644 (The Pile)

Max Activating Token Index: 293

Text #19

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7455. Min Act: -0.0000

Data Index: 1476097 (The Pile)

Max Activating Token Index: 589