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

Dataset: The Pile

Neuron 5036 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2178. Min Range: -1.2178

Max Act: 1.2178. Min Act: -0.0000

Data Index: 783707 (The Pile)

Max Activating Token Index: 89

Text #1

Max Range: 1.2178. Min Range: -1.2178

Max Act: 1.0729. Min Act: -0.0000

Data Index: 1195262 (The Pile)

Max Activating Token Index: 58

Text #2

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.9446. Min Act: -0.0000

Data Index: 1547087 (The Pile)

Max Activating Token Index: 59

Text #3

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.9163. Min Act: -0.0000

Data Index: 1891212 (The Pile)

Max Activating Token Index: 216

Text #4

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.9653. Min Act: -0.0000

Data Index: 1514355 (The Pile)

Max Activating Token Index: 513

Text #5

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.9833. Min Act: -0.0000

Data Index: 837522 (The Pile)

Max Activating Token Index: 190

Text #6

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.8821. Min Act: -0.0000

Data Index: 1798087 (The Pile)

Max Activating Token Index: 780

Text #7

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.9300. Min Act: -0.0000

Data Index: 1233529 (The Pile)

Max Activating Token Index: 161

Text #8

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.9288. Min Act: -0.0000

Data Index: 1835648 (The Pile)

Max Activating Token Index: 159

Text #9

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.8585. Min Act: -0.0000

Data Index: 1563590 (The Pile)

Max Activating Token Index: 881

Text #10

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.9344. Min Act: -0.0000

Data Index: 1392918 (The Pile)

Max Activating Token Index: 889

Text #11

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.9536. Min Act: -0.0000

Data Index: 188217 (The Pile)

Max Activating Token Index: 925

Text #12

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.8724. Min Act: -0.0000

Data Index: 965587 (The Pile)

Max Activating Token Index: 608

Text #13

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.8471. Min Act: -0.0000

Data Index: 870900 (The Pile)

Max Activating Token Index: 795

Text #14

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.9148. Min Act: -0.0000

Data Index: 211382 (The Pile)

Max Activating Token Index: 958

Text #15

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.9622. Min Act: -0.0000

Data Index: 1086355 (The Pile)

Max Activating Token Index: 660

Text #16

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.8679. Min Act: -0.0000

Data Index: 469990 (The Pile)

Max Activating Token Index: 785

Text #17

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.8450. Min Act: -0.0000

Data Index: 497541 (The Pile)

Max Activating Token Index: 264

Text #18

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.8701. Min Act: -0.0000

Data Index: 1544415 (The Pile)

Max Activating Token Index: 476

Text #19

Max Range: 1.2178. Min Range: -1.2178

Max Act: 0.8656. Min Act: -0.0000

Data Index: 207508 (The Pile)

Max Activating Token Index: 79