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

Dataset: The Pile

Neuron 1774 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.6431. Min Act: -0.0000

Data Index: 1098784 (The Pile)

Max Activating Token Index: 246

Text #1

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.4551. Min Act: -0.0000

Data Index: 623008 (The Pile)

Max Activating Token Index: 323

Text #2

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.7959. Min Act: -0.0000

Data Index: 301254 (The Pile)

Max Activating Token Index: 282

Text #3

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.7730. Min Act: -0.0000

Data Index: 1794859 (The Pile)

Max Activating Token Index: 209

Text #4

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.2817. Min Act: -0.0000

Data Index: 1710325 (The Pile)

Max Activating Token Index: 175

Text #5

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.2457. Min Act: -0.0000

Data Index: 1880620 (The Pile)

Max Activating Token Index: 507

Text #6

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.0683. Min Act: -0.0000

Data Index: 200118 (The Pile)

Max Activating Token Index: 133

Text #7

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.0181. Min Act: -0.0000

Data Index: 1180257 (The Pile)

Max Activating Token Index: 570

Text #8

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.1653. Min Act: -0.0000

Data Index: 379632 (The Pile)

Max Activating Token Index: 892

Text #9

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.0152. Min Act: -0.0000

Data Index: 796747 (The Pile)

Max Activating Token Index: 603

Text #10

Max Range: 5.7959. Min Range: -5.7959

Max Act: 4.7096. Min Act: -0.0000

Data Index: 1178968 (The Pile)

Max Activating Token Index: 991

Text #11

Max Range: 5.7959. Min Range: -5.7959

Max Act: 4.8177. Min Act: -0.0000

Data Index: 594027 (The Pile)

Max Activating Token Index: 86

Text #12

Max Range: 5.7959. Min Range: -5.7959

Max Act: 4.9769. Min Act: -0.0000

Data Index: 842341 (The Pile)

Max Activating Token Index: 537

Text #13

Max Range: 5.7959. Min Range: -5.7959

Max Act: 4.9558. Min Act: -0.0000

Data Index: 595285 (The Pile)

Max Activating Token Index: 111

Text #14

Max Range: 5.7959. Min Range: -5.7959

Max Act: 4.5602. Min Act: -0.0000

Data Index: 1194900 (The Pile)

Max Activating Token Index: 228

Text #15

Max Range: 5.7959. Min Range: -5.7959

Max Act: 4.3900. Min Act: -0.0000

Data Index: 1807040 (The Pile)

Max Activating Token Index: 770

Text #16

Max Range: 5.7959. Min Range: -5.7959

Max Act: 4.5725. Min Act: -0.0000

Data Index: 642891 (The Pile)

Max Activating Token Index: 409

Text #17

Max Range: 5.7959. Min Range: -5.7959

Max Act: 4.5561. Min Act: -0.0000

Data Index: 319891 (The Pile)

Max Activating Token Index: 706

Text #18

Max Range: 5.7959. Min Range: -5.7959

Max Act: 4.7138. Min Act: -0.0000

Data Index: 653909 (The Pile)

Max Activating Token Index: 855

Text #19

Max Range: 5.7959. Min Range: -5.7959

Max Act: 4.6933. Min Act: -0.0000

Data Index: 1395626 (The Pile)

Max Activating Token Index: 108