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

Dataset: The Pile

Neuron 3251 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.3037. Min Act: -0.0000

Data Index: 1123534 (The Pile)

Max Activating Token Index: 340

Text #1

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.1995. Min Act: -0.0000

Data Index: 990346 (The Pile)

Max Activating Token Index: 162

Text #2

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.1916. Min Act: -0.0000

Data Index: 1159048 (The Pile)

Max Activating Token Index: 856

Text #3

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.1143. Min Act: -0.0000

Data Index: 490440 (The Pile)

Max Activating Token Index: 466

Text #4

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.1528. Min Act: -0.0000

Data Index: 200971 (The Pile)

Max Activating Token Index: 140

Text #5

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.1631. Min Act: -0.0000

Data Index: 1629229 (The Pile)

Max Activating Token Index: 224

Text #6

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.0124. Min Act: -0.0000

Data Index: 1900278 (The Pile)

Max Activating Token Index: 986

Text #7

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.2153. Min Act: -0.0000

Data Index: 291701 (The Pile)

Max Activating Token Index: 788

Text #8

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.0813. Min Act: -0.0000

Data Index: 515189 (The Pile)

Max Activating Token Index: 116

Text #9

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.1442. Min Act: -0.0000

Data Index: 856910 (The Pile)

Max Activating Token Index: 169

Text #10

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.1325. Min Act: -0.0000

Data Index: 1952467 (The Pile)

Max Activating Token Index: 721

Text #11

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.1404. Min Act: -0.0000

Data Index: 10967 (The Pile)

Max Activating Token Index: 917

Text #12

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.0487. Min Act: -0.0000

Data Index: 1925612 (The Pile)

Max Activating Token Index: 181

Text #13

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.0422. Min Act: -0.0000

Data Index: 1297065 (The Pile)

Max Activating Token Index: 105

Text #14

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.0980. Min Act: -0.0000

Data Index: 1342333 (The Pile)

Max Activating Token Index: 462

Text #15

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.0457. Min Act: -0.0000

Data Index: 1351122 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.1516. Min Act: -0.0000

Data Index: 1638307 (The Pile)

Max Activating Token Index: 131

Text #17

Max Range: 1.3037. Min Range: -1.3037

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1264899 (The Pile)

Max Activating Token Index: 733

Text #18

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.0149. Min Act: -0.0000

Data Index: 1107579 (The Pile)

Max Activating Token Index: 934

Text #19

Max Range: 1.3037. Min Range: -1.3037

Max Act: 0.8844. Min Act: -0.0000

Data Index: 918255 (The Pile)

Max Activating Token Index: 973