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

Dataset: The Pile

Neuron 544 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.6055. Min Act: -0.0000

Data Index: 1253959 (The Pile)

Max Activating Token Index: 424

Text #1

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.5538. Min Act: -0.0000

Data Index: 401111 (The Pile)

Max Activating Token Index: 882

Text #2

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.5114. Min Act: -0.0000

Data Index: 1931076 (The Pile)

Max Activating Token Index: 196

Text #3

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.5180. Min Act: -0.0000

Data Index: 989550 (The Pile)

Max Activating Token Index: 275

Text #4

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4921. Min Act: -0.0000

Data Index: 383622 (The Pile)

Max Activating Token Index: 52

Text #5

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.5207. Min Act: -0.0000

Data Index: 1940154 (The Pile)

Max Activating Token Index: 253

Text #6

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.5135. Min Act: -0.0000

Data Index: 361267 (The Pile)

Max Activating Token Index: 976

Text #7

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1625864 (The Pile)

Max Activating Token Index: 550

Text #8

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.5102. Min Act: -0.0000

Data Index: 653937 (The Pile)

Max Activating Token Index: 743

Text #9

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4894. Min Act: -0.0000

Data Index: 1025297 (The Pile)

Max Activating Token Index: 958

Text #10

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.5040. Min Act: -0.0000

Data Index: 341949 (The Pile)

Max Activating Token Index: 468

Text #11

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1129597 (The Pile)

Max Activating Token Index: 246

Text #12

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4443. Min Act: -0.0001

Data Index: 1447258 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4936. Min Act: -0.0000

Data Index: 1680694 (The Pile)

Max Activating Token Index: 444

Text #14

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4629. Min Act: -0.0000

Data Index: 61421 (The Pile)

Max Activating Token Index: 965

Text #15

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1145160 (The Pile)

Max Activating Token Index: 272

Text #16

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4975. Min Act: -0.0000

Data Index: 1559826 (The Pile)

Max Activating Token Index: 891

Text #17

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4597. Min Act: -0.0000

Data Index: 691026 (The Pile)

Max Activating Token Index: 409

Text #18

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4612. Min Act: -0.0000

Data Index: 483100 (The Pile)

Max Activating Token Index: 83

Text #19

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4414. Min Act: -0.0000

Data Index: 777640 (The Pile)

Max Activating Token Index: 884