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

Dataset: The Pile

Neuron 1104 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: 1.9299. Min Range: -1.9299

Max Act: 1.9299. Min Act: -0.0000

Data Index: 219478 (The Pile)

Max Activating Token Index: 83

Text #1

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.6057. Min Act: -0.0000

Data Index: 241189 (The Pile)

Max Activating Token Index: 273

Text #2

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.3348. Min Act: -0.0000

Data Index: 1653569 (The Pile)

Max Activating Token Index: 233

Text #3

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.1883. Min Act: -0.0000

Data Index: 809589 (The Pile)

Max Activating Token Index: 79

Text #4

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.2521. Min Act: -0.0000

Data Index: 121377 (The Pile)

Max Activating Token Index: 899

Text #5

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.2430. Min Act: -0.0000

Data Index: 1252207 (The Pile)

Max Activating Token Index: 862

Text #6

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.2410. Min Act: -0.0000

Data Index: 58771 (The Pile)

Max Activating Token Index: 61

Text #7

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.2212. Min Act: -0.0000

Data Index: 720934 (The Pile)

Max Activating Token Index: 396

Text #8

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.3278. Min Act: -0.0000

Data Index: 435170 (The Pile)

Max Activating Token Index: 757

Text #9

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.2421. Min Act: -0.0000

Data Index: 1292352 (The Pile)

Max Activating Token Index: 736

Text #10

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.1707. Min Act: -0.0000

Data Index: 1866106 (The Pile)

Max Activating Token Index: 106

Text #11

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.1145. Min Act: -0.0000

Data Index: 1264691 (The Pile)

Max Activating Token Index: 252

Text #12

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.2149. Min Act: -0.0000

Data Index: 883758 (The Pile)

Max Activating Token Index: 998

Text #13

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.2622. Min Act: -0.0000

Data Index: 879288 (The Pile)

Max Activating Token Index: 186

Text #14

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.1555. Min Act: -0.0000

Data Index: 709859 (The Pile)

Max Activating Token Index: 616

Text #15

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.0912. Min Act: -0.0000

Data Index: 937102 (The Pile)

Max Activating Token Index: 676

Text #16

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.1486. Min Act: -0.0000

Data Index: 606658 (The Pile)

Max Activating Token Index: 964

Text #17

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.1471. Min Act: -0.0000

Data Index: 1527814 (The Pile)

Max Activating Token Index: 176

Text #18

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.1416. Min Act: -0.0000

Data Index: 1071425 (The Pile)

Max Activating Token Index: 567

Text #19

Max Range: 1.9299. Min Range: -1.9299

Max Act: 0.9378. Min Act: -0.0000

Data Index: 1655580 (The Pile)

Max Activating Token Index: 750