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

Dataset: The Pile

Neuron 112 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: 0.7249. Min Range: -0.7249

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1256010 (The Pile)

Max Activating Token Index: 1018

Text #1

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5949. Min Act: -0.0000

Data Index: 900993 (The Pile)

Max Activating Token Index: 18

Text #2

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.6301. Min Act: -0.0000

Data Index: 1003150 (The Pile)

Max Activating Token Index: 860

Text #3

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1082884 (The Pile)

Max Activating Token Index: 510

Text #4

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5378. Min Act: -0.0000

Data Index: 1585246 (The Pile)

Max Activating Token Index: 752

Text #5

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5535. Min Act: -0.0000

Data Index: 758117 (The Pile)

Max Activating Token Index: 378

Text #6

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5276. Min Act: -0.0000

Data Index: 1735976 (The Pile)

Max Activating Token Index: 911

Text #7

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4915. Min Act: -0.0000

Data Index: 35817 (The Pile)

Max Activating Token Index: 608

Text #8

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4253. Min Act: -0.0000

Data Index: 199485 (The Pile)

Max Activating Token Index: 782

Text #9

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4547. Min Act: -0.0000

Data Index: 1472500 (The Pile)

Max Activating Token Index: 358

Text #10

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1414823 (The Pile)

Max Activating Token Index: 899

Text #11

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4712. Min Act: -0.0000

Data Index: 208086 (The Pile)

Max Activating Token Index: 848

Text #12

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1979103 (The Pile)

Max Activating Token Index: 164

Text #13

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1954707 (The Pile)

Max Activating Token Index: 480

Text #14

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4257. Min Act: -0.0000

Data Index: 721252 (The Pile)

Max Activating Token Index: 966

Text #15

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4163. Min Act: -0.0000

Data Index: 1488116 (The Pile)

Max Activating Token Index: 272

Text #16

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4673. Min Act: -0.0000

Data Index: 874193 (The Pile)

Max Activating Token Index: 833

Text #17

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1681070 (The Pile)

Max Activating Token Index: 588

Text #18

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.3922. Min Act: -0.0000

Data Index: 1540656 (The Pile)

Max Activating Token Index: 445

Text #19

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4153. Min Act: -0.0000

Data Index: 1225091 (The Pile)

Max Activating Token Index: 243