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

Dataset: The Pile

Neuron 2662 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: 0.2952. Min Range: -0.2952

Max Act: 0.2457. Min Act: -0.0000

Data Index: 1900950 (The Pile)

Max Activating Token Index: 922

Text #1

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2952. Min Act: -0.0000

Data Index: 1990022 (The Pile)

Max Activating Token Index: 609

Text #2

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2278. Min Act: -0.0000

Data Index: 948093 (The Pile)

Max Activating Token Index: 512

Text #3

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2130. Min Act: -0.0000

Data Index: 665923 (The Pile)

Max Activating Token Index: 221

Text #4

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2405. Min Act: -0.0000

Data Index: 1525763 (The Pile)

Max Activating Token Index: 325

Text #5

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2354. Min Act: -0.0000

Data Index: 311020 (The Pile)

Max Activating Token Index: 539

Text #6

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2560. Min Act: -0.0000

Data Index: 504397 (The Pile)

Max Activating Token Index: 855

Text #7

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.1909. Min Act: -0.0000

Data Index: 601375 (The Pile)

Max Activating Token Index: 216

Text #8

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2297. Min Act: -0.0000

Data Index: 877566 (The Pile)

Max Activating Token Index: 25

Text #9

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2159. Min Act: -0.0000

Data Index: 1853868 (The Pile)

Max Activating Token Index: 528

Text #10

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2163. Min Act: -0.0000

Data Index: 358184 (The Pile)

Max Activating Token Index: 125

Text #11

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2152. Min Act: -0.0000

Data Index: 1791123 (The Pile)

Max Activating Token Index: 797

Text #12

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.1929. Min Act: -0.0001

Data Index: 1170933 (The Pile)

Max Activating Token Index: 785

Text #13

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2255. Min Act: -0.0000

Data Index: 1511111 (The Pile)

Max Activating Token Index: 999

Text #14

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.1805. Min Act: -0.0000

Data Index: 715429 (The Pile)

Max Activating Token Index: 317

Text #15

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.1955. Min Act: -0.0000

Data Index: 1317836 (The Pile)

Max Activating Token Index: 837

Text #16

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.1952. Min Act: -0.0000

Data Index: 1400717 (The Pile)

Max Activating Token Index: 290

Text #17

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.1735. Min Act: -0.0000

Data Index: 1768668 (The Pile)

Max Activating Token Index: 805

Text #18

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.1910. Min Act: -0.0000

Data Index: 885970 (The Pile)

Max Activating Token Index: 240

Text #19

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.1778. Min Act: -0.0001

Data Index: 1102595 (The Pile)

Max Activating Token Index: 984