Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2095 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1882. Min Range: -1.1882

Max Act: 1.1882. Min Act: -0.0000

Data Index: 1705741 (The Pile)

Max Activating Token Index: 305

Text #1

Max Range: 1.1882. Min Range: -1.1882

Max Act: 1.0619. Min Act: -0.0000

Data Index: 812702 (The Pile)

Max Activating Token Index: 875

Text #2

Max Range: 1.1882. Min Range: -1.1882

Max Act: 1.0350. Min Act: -0.0000

Data Index: 603947 (The Pile)

Max Activating Token Index: 187

Text #3

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.9869. Min Act: -0.0000

Data Index: 1287074 (The Pile)

Max Activating Token Index: 352

Text #4

Max Range: 1.1882. Min Range: -1.1882

Max Act: 1.0187. Min Act: -0.0000

Data Index: 224776 (The Pile)

Max Activating Token Index: 736

Text #5

Max Range: 1.1882. Min Range: -1.1882

Max Act: 1.0014. Min Act: -0.0000

Data Index: 1117939 (The Pile)

Max Activating Token Index: 684

Text #6

Max Range: 1.1882. Min Range: -1.1882

Max Act: 1.0578. Min Act: -0.0000

Data Index: 1471253 (The Pile)

Max Activating Token Index: 762

Text #7

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.9368. Min Act: -0.0000

Data Index: 827772 (The Pile)

Max Activating Token Index: 337

Text #8

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.9880. Min Act: -0.0000

Data Index: 1237938 (The Pile)

Max Activating Token Index: 499

Text #9

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.9416. Min Act: -0.0000

Data Index: 1216567 (The Pile)

Max Activating Token Index: 571

Text #10

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.9298. Min Act: -0.0000

Data Index: 1063981 (The Pile)

Max Activating Token Index: 169

Text #11

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.9213. Min Act: -0.0000

Data Index: 323495 (The Pile)

Max Activating Token Index: 453

Text #12

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.9045. Min Act: -0.0000

Data Index: 1307831 (The Pile)

Max Activating Token Index: 169

Text #13

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.8961. Min Act: -0.0000

Data Index: 130115 (The Pile)

Max Activating Token Index: 427

Text #14

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.8402. Min Act: -0.0000

Data Index: 1820701 (The Pile)

Max Activating Token Index: 977

Text #15

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1936603 (The Pile)

Max Activating Token Index: 123

Text #16

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.9086. Min Act: -0.0000

Data Index: 273338 (The Pile)

Max Activating Token Index: 185

Text #17

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.9434. Min Act: -0.0000

Data Index: 685383 (The Pile)

Max Activating Token Index: 160

Text #18

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.9033. Min Act: -0.0000

Data Index: 1540793 (The Pile)

Max Activating Token Index: 497

Text #19

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.8205. Min Act: -0.0000

Data Index: 1219885 (The Pile)

Max Activating Token Index: 516