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

Dataset: The Pile

Neuron 3665 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: 1.7094. Min Range: -1.7094

Max Act: 1.7094. Min Act: -0.0000

Data Index: 412118 (The Pile)

Max Activating Token Index: 77

Text #1

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.6426. Min Act: -0.0000

Data Index: 488602 (The Pile)

Max Activating Token Index: 999

Text #2

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.4085. Min Act: -0.0000

Data Index: 1475982 (The Pile)

Max Activating Token Index: 533

Text #3

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.4454. Min Act: -0.0000

Data Index: 1763224 (The Pile)

Max Activating Token Index: 998

Text #4

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.3601. Min Act: -0.0000

Data Index: 1096850 (The Pile)

Max Activating Token Index: 944

Text #5

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.2738. Min Act: -0.0000

Data Index: 1724583 (The Pile)

Max Activating Token Index: 288

Text #6

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.4256. Min Act: -0.0000

Data Index: 1520474 (The Pile)

Max Activating Token Index: 56

Text #7

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.5000. Min Act: -0.0000

Data Index: 1889906 (The Pile)

Max Activating Token Index: 808

Text #8

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.3407. Min Act: -0.0000

Data Index: 1954422 (The Pile)

Max Activating Token Index: 707

Text #9

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.3154. Min Act: -0.0000

Data Index: 1803131 (The Pile)

Max Activating Token Index: 35

Text #10

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.2394. Min Act: -0.0000

Data Index: 1725012 (The Pile)

Max Activating Token Index: 455

Text #11

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.2427. Min Act: -0.0000

Data Index: 584135 (The Pile)

Max Activating Token Index: 923

Text #12

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.1277. Min Act: -0.0000

Data Index: 1508885 (The Pile)

Max Activating Token Index: 650

Text #13

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.2225. Min Act: -0.0000

Data Index: 755988 (The Pile)

Max Activating Token Index: 549

Text #14

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.2088. Min Act: -0.0000

Data Index: 382112 (The Pile)

Max Activating Token Index: 34

Text #15

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.2022. Min Act: -0.0000

Data Index: 839358 (The Pile)

Max Activating Token Index: 411

Text #16

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.2552. Min Act: -0.0000

Data Index: 616647 (The Pile)

Max Activating Token Index: 1007

Text #17

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.1149. Min Act: -0.0000

Data Index: 710680 (The Pile)

Max Activating Token Index: 232

Text #18

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.0883. Min Act: -0.0000

Data Index: 1451330 (The Pile)

Max Activating Token Index: 1005

Text #19

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.1604. Min Act: -0.0000

Data Index: 1105008 (The Pile)

Max Activating Token Index: 232