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

Dataset: The Pile

Neuron 3556 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1225. Min Range: -7.1225

Max Act: 7.1225. Min Act: -0.0000

Data Index: 1354438 (The Pile)

Max Activating Token Index: 689

Text #1

Max Range: 7.1225. Min Range: -7.1225

Max Act: 7.1175. Min Act: -0.0000

Data Index: 1138226 (The Pile)

Max Activating Token Index: 320

Text #2

Max Range: 7.1225. Min Range: -7.1225

Max Act: 7.1203. Min Act: -0.0000

Data Index: 273901 (The Pile)

Max Activating Token Index: 821

Text #3

Max Range: 7.1225. Min Range: -7.1225

Max Act: 6.8540. Min Act: -0.0000

Data Index: 1080465 (The Pile)

Max Activating Token Index: 666

Text #4

Max Range: 7.1225. Min Range: -7.1225

Max Act: 6.8315. Min Act: -0.0000

Data Index: 285351 (The Pile)

Max Activating Token Index: 104

Text #5

Max Range: 7.1225. Min Range: -7.1225

Max Act: 6.4906. Min Act: -0.0000

Data Index: 994335 (The Pile)

Max Activating Token Index: 241

Text #6

Max Range: 7.1225. Min Range: -7.1225

Max Act: 6.4493. Min Act: -0.0000

Data Index: 745961 (The Pile)

Max Activating Token Index: 77

Text #7

Max Range: 7.1225. Min Range: -7.1225

Max Act: 6.2927. Min Act: -0.0000

Data Index: 481211 (The Pile)

Max Activating Token Index: 595

Text #8

Max Range: 7.1225. Min Range: -7.1225

Max Act: 6.2990. Min Act: -0.0000

Data Index: 1574250 (The Pile)

Max Activating Token Index: 87

Text #9

Max Range: 7.1225. Min Range: -7.1225

Max Act: 6.1421. Min Act: -0.0000

Data Index: 1297065 (The Pile)

Max Activating Token Index: 285

Text #10

Max Range: 7.1225. Min Range: -7.1225

Max Act: 6.3454. Min Act: -0.0000

Data Index: 19714 (The Pile)

Max Activating Token Index: 43

Text #11

Max Range: 7.1225. Min Range: -7.1225

Max Act: 6.0532. Min Act: -0.0000

Data Index: 1792866 (The Pile)

Max Activating Token Index: 530

Text #12

Max Range: 7.1225. Min Range: -7.1225

Max Act: 6.0161. Min Act: -0.0000

Data Index: 1190791 (The Pile)

Max Activating Token Index: 720

Text #13

Max Range: 7.1225. Min Range: -7.1225

Max Act: 5.8358. Min Act: -0.0000

Data Index: 175584 (The Pile)

Max Activating Token Index: 539

Text #14

Max Range: 7.1225. Min Range: -7.1225

Max Act: 6.1662. Min Act: -0.0000

Data Index: 1721493 (The Pile)

Max Activating Token Index: 40

Text #15

Max Range: 7.1225. Min Range: -7.1225

Max Act: 5.9233. Min Act: -0.0000

Data Index: 1110097 (The Pile)

Max Activating Token Index: 341

Text #16

Max Range: 7.1225. Min Range: -7.1225

Max Act: 6.0677. Min Act: -0.0000

Data Index: 126161 (The Pile)

Max Activating Token Index: 600

Text #17

Max Range: 7.1225. Min Range: -7.1225

Max Act: 5.6765. Min Act: -0.0000

Data Index: 879946 (The Pile)

Max Activating Token Index: 338

Text #18

Max Range: 7.1225. Min Range: -7.1225

Max Act: 5.8045. Min Act: -0.0000

Data Index: 1949829 (The Pile)

Max Activating Token Index: 85

Text #19

Max Range: 7.1225. Min Range: -7.1225

Max Act: 5.3814. Min Act: -0.0000

Data Index: 1127093 (The Pile)

Max Activating Token Index: 737