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

Dataset: The Pile

Neuron 4675 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1662. Min Act: -0.0000

Data Index: 916808 (The Pile)

Max Activating Token Index: 439

Text #1

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1333311 (The Pile)

Max Activating Token Index: 312

Text #2

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1646. Min Act: -0.0000

Data Index: 106898 (The Pile)

Max Activating Token Index: 566

Text #3

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1529. Min Act: -0.0000

Data Index: 1982778 (The Pile)

Max Activating Token Index: 407

Text #4

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1426. Min Act: -0.0000

Data Index: 1686942 (The Pile)

Max Activating Token Index: 303

Text #5

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1527. Min Act: -0.0000

Data Index: 221940 (The Pile)

Max Activating Token Index: 276

Text #6

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1403. Min Act: -0.0000

Data Index: 1179204 (The Pile)

Max Activating Token Index: 404

Text #7

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1421. Min Act: -0.0000

Data Index: 1063734 (The Pile)

Max Activating Token Index: 625

Text #8

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1308. Min Act: -0.0000

Data Index: 313267 (The Pile)

Max Activating Token Index: 420

Text #9

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1327. Min Act: -0.0000

Data Index: 1192020 (The Pile)

Max Activating Token Index: 265

Text #10

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1371. Min Act: -0.0000

Data Index: 1080680 (The Pile)

Max Activating Token Index: 512

Text #11

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1236686 (The Pile)

Max Activating Token Index: 775

Text #12

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1245. Min Act: -0.0000

Data Index: 1267995 (The Pile)

Max Activating Token Index: 398

Text #13

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1062. Min Act: -0.0000

Data Index: 887920 (The Pile)

Max Activating Token Index: 903

Text #14

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1249. Min Act: -0.0000

Data Index: 716217 (The Pile)

Max Activating Token Index: 320

Text #15

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1294. Min Act: -0.0000

Data Index: 242225 (The Pile)

Max Activating Token Index: 127

Text #16

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1187. Min Act: -0.0000

Data Index: 1985849 (The Pile)

Max Activating Token Index: 541

Text #17

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1174. Min Act: -0.0000

Data Index: 908166 (The Pile)

Max Activating Token Index: 435

Text #18

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1435768 (The Pile)

Max Activating Token Index: 61

Text #19

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1577809 (The Pile)

Max Activating Token Index: 740