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

Dataset: The Pile

Neuron 155 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: 0.9213. Min Range: -0.9213

Max Act: 0.8354. Min Act: -0.0000

Data Index: 324302 (The Pile)

Max Activating Token Index: 911

Text #1

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.8648. Min Act: -0.0000

Data Index: 316242 (The Pile)

Max Activating Token Index: 458

Text #2

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.8538. Min Act: -0.0000

Data Index: 128726 (The Pile)

Max Activating Token Index: 530

Text #3

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.8285. Min Act: -0.0000

Data Index: 1430641 (The Pile)

Max Activating Token Index: 660

Text #4

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.9213. Min Act: -0.0000

Data Index: 1933172 (The Pile)

Max Activating Token Index: 809

Text #5

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.8052. Min Act: -0.0000

Data Index: 157344 (The Pile)

Max Activating Token Index: 563

Text #6

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.7329. Min Act: -0.0000

Data Index: 354798 (The Pile)

Max Activating Token Index: 347

Text #7

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.8119. Min Act: -0.0000

Data Index: 1493749 (The Pile)

Max Activating Token Index: 758

Text #8

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.7562. Min Act: -0.0000

Data Index: 245040 (The Pile)

Max Activating Token Index: 165

Text #9

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.7949. Min Act: -0.0000

Data Index: 187385 (The Pile)

Max Activating Token Index: 237

Text #10

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.7593. Min Act: -0.0000

Data Index: 720516 (The Pile)

Max Activating Token Index: 864

Text #11

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.8138. Min Act: -0.0000

Data Index: 1647150 (The Pile)

Max Activating Token Index: 873

Text #12

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.8149. Min Act: -0.0000

Data Index: 1000960 (The Pile)

Max Activating Token Index: 676

Text #13

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.7834. Min Act: -0.0000

Data Index: 1759241 (The Pile)

Max Activating Token Index: 940

Text #14

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.8231. Min Act: -0.0000

Data Index: 1982919 (The Pile)

Max Activating Token Index: 907

Text #15

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.8160. Min Act: -0.0000

Data Index: 741762 (The Pile)

Max Activating Token Index: 676

Text #16

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.7888. Min Act: -0.0000

Data Index: 1689870 (The Pile)

Max Activating Token Index: 910

Text #17

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.7598. Min Act: -0.0000

Data Index: 23315 (The Pile)

Max Activating Token Index: 370

Text #18

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.7562. Min Act: -0.0000

Data Index: 1524667 (The Pile)

Max Activating Token Index: 929

Text #19

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1046975 (The Pile)

Max Activating Token Index: 950