Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1979 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.9961. Min Act: -0.0000

Data Index: 1906800 (The Pile)

Max Activating Token Index: 526

Text #1

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8954. Min Act: -0.0000

Data Index: 570633 (The Pile)

Max Activating Token Index: 518

Text #2

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8316. Min Act: -0.0000

Data Index: 1670501 (The Pile)

Max Activating Token Index: 598

Text #3

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1260723 (The Pile)

Max Activating Token Index: 984

Text #4

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8493. Min Act: -0.0000

Data Index: 776104 (The Pile)

Max Activating Token Index: 674

Text #5

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8631. Min Act: -0.0000

Data Index: 425535 (The Pile)

Max Activating Token Index: 484

Text #6

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.7760. Min Act: -0.0000

Data Index: 154774 (The Pile)

Max Activating Token Index: 644

Text #7

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8137. Min Act: -0.0000

Data Index: 910354 (The Pile)

Max Activating Token Index: 647

Text #8

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8221. Min Act: -0.0000

Data Index: 1560942 (The Pile)

Max Activating Token Index: 297

Text #9

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8200. Min Act: -0.0000

Data Index: 1855613 (The Pile)

Max Activating Token Index: 537

Text #10

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8321. Min Act: -0.0000

Data Index: 741344 (The Pile)

Max Activating Token Index: 647

Text #11

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.7407. Min Act: -0.0000

Data Index: 1925240 (The Pile)

Max Activating Token Index: 75

Text #12

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8073. Min Act: -0.0000

Data Index: 504900 (The Pile)

Max Activating Token Index: 56

Text #13

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8110. Min Act: -0.0000

Data Index: 1661067 (The Pile)

Max Activating Token Index: 122

Text #14

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8049. Min Act: -0.0000

Data Index: 1437613 (The Pile)

Max Activating Token Index: 106

Text #15

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.7834. Min Act: -0.0000

Data Index: 1106723 (The Pile)

Max Activating Token Index: 251

Text #16

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.8055. Min Act: -0.0000

Data Index: 1050327 (The Pile)

Max Activating Token Index: 381

Text #17

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.7233. Min Act: -0.0000

Data Index: 947901 (The Pile)

Max Activating Token Index: 751

Text #18

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.7718. Min Act: -0.0000

Data Index: 1632874 (The Pile)

Max Activating Token Index: 7

Text #19

Max Range: 0.9961. Min Range: -0.9961

Max Act: 0.7708. Min Act: -0.0000

Data Index: 366993 (The Pile)

Max Activating Token Index: 979