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

Dataset: The Pile

Neuron 1327 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: 3.1010. Min Range: -3.1010

Max Act: 3.1010. Min Act: -0.0000

Data Index: 1091904 (The Pile)

Max Activating Token Index: 451

Text #1

Max Range: 3.1010. Min Range: -3.1010

Max Act: 2.3445. Min Act: -0.0000

Data Index: 1303138 (The Pile)

Max Activating Token Index: 693

Text #2

Max Range: 3.1010. Min Range: -3.1010

Max Act: 2.1692. Min Act: -0.0000

Data Index: 448226 (The Pile)

Max Activating Token Index: 741

Text #3

Max Range: 3.1010. Min Range: -3.1010

Max Act: 2.5772. Min Act: -0.0000

Data Index: 1565970 (The Pile)

Max Activating Token Index: 185

Text #4

Max Range: 3.1010. Min Range: -3.1010

Max Act: 2.4485. Min Act: -0.0000

Data Index: 1374761 (The Pile)

Max Activating Token Index: 257

Text #5

Max Range: 3.1010. Min Range: -3.1010

Max Act: 2.5630. Min Act: -0.0000

Data Index: 144972 (The Pile)

Max Activating Token Index: 658

Text #6

Max Range: 3.1010. Min Range: -3.1010

Max Act: 2.2235. Min Act: -0.0000

Data Index: 965634 (The Pile)

Max Activating Token Index: 978

Text #7

Max Range: 3.1010. Min Range: -3.1010

Max Act: 2.1689. Min Act: -0.0000

Data Index: 257517 (The Pile)

Max Activating Token Index: 658

Text #8

Max Range: 3.1010. Min Range: -3.1010

Max Act: 1.8262. Min Act: -0.0000

Data Index: 637231 (The Pile)

Max Activating Token Index: 997

Text #9

Max Range: 3.1010. Min Range: -3.1010

Max Act: 2.2464. Min Act: -0.0000

Data Index: 1220649 (The Pile)

Max Activating Token Index: 766

Text #10

Max Range: 3.1010. Min Range: -3.1010

Max Act: 2.2175. Min Act: -0.0000

Data Index: 1456054 (The Pile)

Max Activating Token Index: 420

Text #11

Max Range: 3.1010. Min Range: -3.1010

Max Act: 2.5619. Min Act: -0.0000

Data Index: 1777870 (The Pile)

Max Activating Token Index: 253

Text #12

Max Range: 3.1010. Min Range: -3.1010

Max Act: 1.9451. Min Act: -0.0000

Data Index: 68964 (The Pile)

Max Activating Token Index: 855

Text #13

Max Range: 3.1010. Min Range: -3.1010

Max Act: 2.1426. Min Act: -0.0000

Data Index: 1379448 (The Pile)

Max Activating Token Index: 183

Text #14

Max Range: 3.1010. Min Range: -3.1010

Max Act: 1.9981. Min Act: -0.0000

Data Index: 479550 (The Pile)

Max Activating Token Index: 154

Text #15

Max Range: 3.1010. Min Range: -3.1010

Max Act: 1.8668. Min Act: -0.0000

Data Index: 1317392 (The Pile)

Max Activating Token Index: 470

Text #16

Max Range: 3.1010. Min Range: -3.1010

Max Act: 1.9371. Min Act: -0.0000

Data Index: 790955 (The Pile)

Max Activating Token Index: 553

Text #17

Max Range: 3.1010. Min Range: -3.1010

Max Act: 1.7185. Min Act: -0.0000

Data Index: 615419 (The Pile)

Max Activating Token Index: 923

Text #18

Max Range: 3.1010. Min Range: -3.1010

Max Act: 1.8957. Min Act: -0.0000

Data Index: 331521 (The Pile)

Max Activating Token Index: 564

Text #19

Max Range: 3.1010. Min Range: -3.1010

Max Act: 1.8826. Min Act: -0.0000

Data Index: 1561406 (The Pile)

Max Activating Token Index: 559