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

Dataset: The Pile

Neuron 1070 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: 0.3078. Min Range: -0.3078

Max Act: 0.2778. Min Act: -0.0000

Data Index: 530631 (The Pile)

Max Activating Token Index: 245

Text #1

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.3078. Min Act: -0.0000

Data Index: 1213813 (The Pile)

Max Activating Token Index: 529

Text #2

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2527. Min Act: -0.0000

Data Index: 923419 (The Pile)

Max Activating Token Index: 306

Text #3

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2439. Min Act: -0.0000

Data Index: 98000 (The Pile)

Max Activating Token Index: 47

Text #4

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2432. Min Act: -0.0000

Data Index: 1324927 (The Pile)

Max Activating Token Index: 303

Text #5

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2419. Min Act: -0.0000

Data Index: 479848 (The Pile)

Max Activating Token Index: 63

Text #6

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2253. Min Act: -0.0000

Data Index: 907324 (The Pile)

Max Activating Token Index: 499

Text #7

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1091323 (The Pile)

Max Activating Token Index: 875

Text #8

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1480287 (The Pile)

Max Activating Token Index: 111

Text #9

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2424. Min Act: -0.0000

Data Index: 81130 (The Pile)

Max Activating Token Index: 37

Text #10

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2316. Min Act: -0.0000

Data Index: 1628242 (The Pile)

Max Activating Token Index: 299

Text #11

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2323. Min Act: -0.0000

Data Index: 232787 (The Pile)

Max Activating Token Index: 784

Text #12

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1488582 (The Pile)

Max Activating Token Index: 29

Text #13

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2225. Min Act: -0.0000

Data Index: 353197 (The Pile)

Max Activating Token Index: 73

Text #14

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2182. Min Act: -0.0000

Data Index: 83097 (The Pile)

Max Activating Token Index: 616

Text #15

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2223. Min Act: -0.0000

Data Index: 1826133 (The Pile)

Max Activating Token Index: 404

Text #16

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1589594 (The Pile)

Max Activating Token Index: 863

Text #17

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2213. Min Act: -0.0000

Data Index: 739521 (The Pile)

Max Activating Token Index: 710

Text #18

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2189. Min Act: -0.0000

Data Index: 500540 (The Pile)

Max Activating Token Index: 767

Text #19

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2095. Min Act: -0.0000

Data Index: 1578361 (The Pile)

Max Activating Token Index: 139