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

Dataset: The Pile

Neuron 3107 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.9030. Min Act: -0.0000

Data Index: 1694124 (The Pile)

Max Activating Token Index: 271

Text #1

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.7834. Min Act: -0.0000

Data Index: 1065908 (The Pile)

Max Activating Token Index: 559

Text #2

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.7441. Min Act: -0.0000

Data Index: 20696 (The Pile)

Max Activating Token Index: 1003

Text #3

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.7483. Min Act: -0.0000

Data Index: 1840932 (The Pile)

Max Activating Token Index: 378

Text #4

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.7149. Min Act: -0.0000

Data Index: 897343 (The Pile)

Max Activating Token Index: 845

Text #5

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6471. Min Act: -0.0000

Data Index: 935610 (The Pile)

Max Activating Token Index: 190

Text #6

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6374. Min Act: -0.0000

Data Index: 410440 (The Pile)

Max Activating Token Index: 78

Text #7

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6137. Min Act: -0.0000

Data Index: 1219037 (The Pile)

Max Activating Token Index: 926

Text #8

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.5851. Min Act: -0.0000

Data Index: 1282433 (The Pile)

Max Activating Token Index: 35

Text #9

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6180. Min Act: -0.0000

Data Index: 837685 (The Pile)

Max Activating Token Index: 762

Text #10

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6612. Min Act: -0.0000

Data Index: 532568 (The Pile)

Max Activating Token Index: 695

Text #11

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6144. Min Act: -0.0000

Data Index: 779149 (The Pile)

Max Activating Token Index: 934

Text #12

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6113. Min Act: -0.0000

Data Index: 1552766 (The Pile)

Max Activating Token Index: 346

Text #13

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.5946. Min Act: -0.0000

Data Index: 306583 (The Pile)

Max Activating Token Index: 592

Text #14

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1890871 (The Pile)

Max Activating Token Index: 762

Text #15

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.5695. Min Act: -0.0000

Data Index: 737813 (The Pile)

Max Activating Token Index: 717

Text #16

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.5888. Min Act: -0.0000

Data Index: 1022983 (The Pile)

Max Activating Token Index: 466

Text #17

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.5859. Min Act: -0.0000

Data Index: 293563 (The Pile)

Max Activating Token Index: 353

Text #18

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.5871. Min Act: -0.0000

Data Index: 1731412 (The Pile)

Max Activating Token Index: 408

Text #19

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6056. Min Act: -0.0000

Data Index: 1100711 (The Pile)

Max Activating Token Index: 93