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

Dataset: The Pile

Neuron 2755 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: 0.1888. Min Range: -0.1888

Max Act: 0.1888. Min Act: 0.0000

Data Index: 638916 (The Pile)

Max Activating Token Index: 79

Text #1

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1555. Min Act: 0.0000

Data Index: 307012 (The Pile)

Max Activating Token Index: 611

Text #2

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1478. Min Act: -0.0000

Data Index: 736196 (The Pile)

Max Activating Token Index: 170

Text #3

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1328. Min Act: -0.0000

Data Index: 850010 (The Pile)

Max Activating Token Index: 679

Text #4

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1149. Min Act: 0.0000

Data Index: 1109712 (The Pile)

Max Activating Token Index: 271

Text #5

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1104. Min Act: -0.0000

Data Index: 1831389 (The Pile)

Max Activating Token Index: 211

Text #6

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1138. Min Act: -0.0000

Data Index: 340349 (The Pile)

Max Activating Token Index: 330

Text #7

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1280. Min Act: -0.0000

Data Index: 43108 (The Pile)

Max Activating Token Index: 534

Text #8

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1555326 (The Pile)

Max Activating Token Index: 691

Text #9

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1096. Min Act: -0.0000

Data Index: 165445 (The Pile)

Max Activating Token Index: 373

Text #10

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1000. Min Act: 0.0000

Data Index: 1341429 (The Pile)

Max Activating Token Index: 535

Text #11

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1147. Min Act: -0.0000

Data Index: 924643 (The Pile)

Max Activating Token Index: 829

Text #12

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1089. Min Act: -0.0000

Data Index: 1896703 (The Pile)

Max Activating Token Index: 616

Text #13

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1143. Min Act: -0.0000

Data Index: 385044 (The Pile)

Max Activating Token Index: 62

Text #14

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1133. Min Act: -0.0000

Data Index: 291092 (The Pile)

Max Activating Token Index: 543

Text #15

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1071. Min Act: -0.0000

Data Index: 321748 (The Pile)

Max Activating Token Index: 81

Text #16

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1055. Min Act: -0.0000

Data Index: 640780 (The Pile)

Max Activating Token Index: 362

Text #17

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1129. Min Act: 0.0000

Data Index: 254187 (The Pile)

Max Activating Token Index: 435

Text #18

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1079. Min Act: -0.0000

Data Index: 707076 (The Pile)

Max Activating Token Index: 473

Text #19

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1076. Min Act: -0.0000

Data Index: 1113820 (The Pile)

Max Activating Token Index: 367