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

Dataset: The Pile

Neuron 67 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: 1.3642. Min Range: -1.3642

Max Act: 1.3642. Min Act: -0.0000

Data Index: 1666920 (The Pile)

Max Activating Token Index: 193

Text #1

Max Range: 1.3642. Min Range: -1.3642

Max Act: 1.2968. Min Act: -0.0000

Data Index: 597925 (The Pile)

Max Activating Token Index: 774

Text #2

Max Range: 1.3642. Min Range: -1.3642

Max Act: 1.1276. Min Act: -0.0000

Data Index: 1966285 (The Pile)

Max Activating Token Index: 221

Text #3

Max Range: 1.3642. Min Range: -1.3642

Max Act: 1.0814. Min Act: -0.0000

Data Index: 1114928 (The Pile)

Max Activating Token Index: 104

Text #4

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.9776. Min Act: -0.0000

Data Index: 114710 (The Pile)

Max Activating Token Index: 499

Text #5

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.9915. Min Act: -0.0000

Data Index: 990247 (The Pile)

Max Activating Token Index: 900

Text #6

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.9265. Min Act: -0.0000

Data Index: 1789516 (The Pile)

Max Activating Token Index: 409

Text #7

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.9744. Min Act: -0.0000

Data Index: 656245 (The Pile)

Max Activating Token Index: 273

Text #8

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.9423. Min Act: -0.0000

Data Index: 1691214 (The Pile)

Max Activating Token Index: 101

Text #9

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.9112. Min Act: -0.0000

Data Index: 1264464 (The Pile)

Max Activating Token Index: 63

Text #10

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.9621. Min Act: -0.0000

Data Index: 1155032 (The Pile)

Max Activating Token Index: 54

Text #11

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.9374. Min Act: -0.0000

Data Index: 1035229 (The Pile)

Max Activating Token Index: 464

Text #12

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.9196. Min Act: -0.0000

Data Index: 547709 (The Pile)

Max Activating Token Index: 228

Text #13

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.9044. Min Act: -0.0000

Data Index: 145968 (The Pile)

Max Activating Token Index: 705

Text #14

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.9129. Min Act: -0.0000

Data Index: 950850 (The Pile)

Max Activating Token Index: 952

Text #15

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.8949. Min Act: -0.0000

Data Index: 278823 (The Pile)

Max Activating Token Index: 713

Text #16

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.8921. Min Act: -0.0000

Data Index: 1079429 (The Pile)

Max Activating Token Index: 372

Text #17

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.9080. Min Act: -0.0000

Data Index: 1306098 (The Pile)

Max Activating Token Index: 76

Text #18

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.9052. Min Act: -0.0000

Data Index: 1743001 (The Pile)

Max Activating Token Index: 796

Text #19

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.8649. Min Act: -0.0000

Data Index: 1839194 (The Pile)

Max Activating Token Index: 933