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

Dataset: The Pile

Neuron 3043 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2288. Min Range: -1.2288

Max Act: 1.2288. Min Act: -0.0000

Data Index: 505733 (The Pile)

Max Activating Token Index: 737

Text #1

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.9911. Min Act: -0.0000

Data Index: 1192909 (The Pile)

Max Activating Token Index: 416

Text #2

Max Range: 1.2288. Min Range: -1.2288

Max Act: 1.0140. Min Act: -0.0000

Data Index: 1167218 (The Pile)

Max Activating Token Index: 775

Text #3

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.9196. Min Act: -0.0000

Data Index: 585543 (The Pile)

Max Activating Token Index: 946

Text #4

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.9020. Min Act: -0.0000

Data Index: 1508541 (The Pile)

Max Activating Token Index: 705

Text #5

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.9252. Min Act: -0.0000

Data Index: 918125 (The Pile)

Max Activating Token Index: 733

Text #6

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.6688. Min Act: -0.0000

Data Index: 306594 (The Pile)

Max Activating Token Index: 873

Text #7

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.8427. Min Act: -0.0000

Data Index: 1263560 (The Pile)

Max Activating Token Index: 120

Text #8

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.8200. Min Act: -0.0000

Data Index: 383471 (The Pile)

Max Activating Token Index: 915

Text #9

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.7643. Min Act: -0.0000

Data Index: 923663 (The Pile)

Max Activating Token Index: 193

Text #10

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.7085. Min Act: -0.0000

Data Index: 760661 (The Pile)

Max Activating Token Index: 955

Text #11

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.7470. Min Act: -0.0000

Data Index: 947240 (The Pile)

Max Activating Token Index: 274

Text #12

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.7454. Min Act: -0.0000

Data Index: 1329328 (The Pile)

Max Activating Token Index: 129

Text #13

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.7771. Min Act: -0.0000

Data Index: 215743 (The Pile)

Max Activating Token Index: 189

Text #14

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.7090. Min Act: -0.0000

Data Index: 1867774 (The Pile)

Max Activating Token Index: 192

Text #15

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.7331. Min Act: -0.0000

Data Index: 1718224 (The Pile)

Max Activating Token Index: 548

Text #16

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.6859. Min Act: -0.0000

Data Index: 224812 (The Pile)

Max Activating Token Index: 581

Text #17

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.6864. Min Act: -0.0000

Data Index: 1504784 (The Pile)

Max Activating Token Index: 600

Text #18

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.7134. Min Act: -0.0000

Data Index: 1044263 (The Pile)

Max Activating Token Index: 60

Text #19

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.7420. Min Act: -0.0000

Data Index: 957639 (The Pile)

Max Activating Token Index: 901