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

Dataset: The Pile

Neuron 2415 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.6133. Min Act: -0.0000

Data Index: 457943 (The Pile)

Max Activating Token Index: 436

Text #1

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5669. Min Act: -0.0000

Data Index: 1489934 (The Pile)

Max Activating Token Index: 837

Text #2

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4888. Min Act: 0.0000

Data Index: 1443313 (The Pile)

Max Activating Token Index: 260

Text #3

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4859. Min Act: 0.0000

Data Index: 1531322 (The Pile)

Max Activating Token Index: 311

Text #4

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4775. Min Act: -0.0000

Data Index: 564494 (The Pile)

Max Activating Token Index: 683

Text #5

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4553. Min Act: -0.0000

Data Index: 1693360 (The Pile)

Max Activating Token Index: 532

Text #6

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4397. Min Act: -0.0000

Data Index: 80283 (The Pile)

Max Activating Token Index: 580

Text #7

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4276. Min Act: -0.0000

Data Index: 1016771 (The Pile)

Max Activating Token Index: 994

Text #8

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4292. Min Act: -0.0000

Data Index: 533929 (The Pile)

Max Activating Token Index: 854

Text #9

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4393. Min Act: 0.0001

Data Index: 1192905 (The Pile)

Max Activating Token Index: 688

Text #10

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1368328 (The Pile)

Max Activating Token Index: 37

Text #11

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1815587 (The Pile)

Max Activating Token Index: 853

Text #12

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1987428 (The Pile)

Max Activating Token Index: 36

Text #13

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4012. Min Act: -0.0000

Data Index: 898637 (The Pile)

Max Activating Token Index: 376

Text #14

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4071. Min Act: 0.0000

Data Index: 803537 (The Pile)

Max Activating Token Index: 965

Text #15

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4087. Min Act: -0.0000

Data Index: 732640 (The Pile)

Max Activating Token Index: 963

Text #16

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4618. Min Act: -0.0000

Data Index: 1044045 (The Pile)

Max Activating Token Index: 705

Text #17

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4188. Min Act: -0.0000

Data Index: 1061239 (The Pile)

Max Activating Token Index: 162

Text #18

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1350051 (The Pile)

Max Activating Token Index: 467

Text #19

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.3733. Min Act: -0.0000

Data Index: 1318402 (The Pile)

Max Activating Token Index: 316