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

Dataset: The Pile

Neuron 1212 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0445. Min Range: -5.0445

Max Act: 4.8368. Min Act: -0.0000

Data Index: 1670253 (The Pile)

Max Activating Token Index: 239

Text #1

Max Range: 5.0445. Min Range: -5.0445

Max Act: 4.4872. Min Act: -0.0000

Data Index: 885557 (The Pile)

Max Activating Token Index: 205

Text #2

Max Range: 5.0445. Min Range: -5.0445

Max Act: 5.0445. Min Act: -0.0000

Data Index: 498041 (The Pile)

Max Activating Token Index: 159

Text #3

Max Range: 5.0445. Min Range: -5.0445

Max Act: 4.4712. Min Act: -0.0000

Data Index: 1251633 (The Pile)

Max Activating Token Index: 117

Text #4

Max Range: 5.0445. Min Range: -5.0445

Max Act: 4.3001. Min Act: -0.0000

Data Index: 1978690 (The Pile)

Max Activating Token Index: 42

Text #5

Max Range: 5.0445. Min Range: -5.0445

Max Act: 4.3029. Min Act: -0.0000

Data Index: 483739 (The Pile)

Max Activating Token Index: 92

Text #6

Max Range: 5.0445. Min Range: -5.0445

Max Act: 4.0404. Min Act: -0.0000

Data Index: 1284612 (The Pile)

Max Activating Token Index: 569

Text #7

Max Range: 5.0445. Min Range: -5.0445

Max Act: 3.9686. Min Act: -0.0000

Data Index: 1110132 (The Pile)

Max Activating Token Index: 145

Text #8

Max Range: 5.0445. Min Range: -5.0445

Max Act: 3.9150. Min Act: -0.0000

Data Index: 1144677 (The Pile)

Max Activating Token Index: 131

Text #9

Max Range: 5.0445. Min Range: -5.0445

Max Act: 3.9807. Min Act: -0.0000

Data Index: 780810 (The Pile)

Max Activating Token Index: 256

Text #10

Max Range: 5.0445. Min Range: -5.0445

Max Act: 4.0433. Min Act: -0.0000

Data Index: 1472385 (The Pile)

Max Activating Token Index: 410

Text #11

Max Range: 5.0445. Min Range: -5.0445

Max Act: 3.6645. Min Act: -0.0000

Data Index: 53131 (The Pile)

Max Activating Token Index: 86

Text #12

Max Range: 5.0445. Min Range: -5.0445

Max Act: 3.7440. Min Act: -0.0000

Data Index: 708550 (The Pile)

Max Activating Token Index: 33

Text #13

Max Range: 5.0445. Min Range: -5.0445

Max Act: 3.5002. Min Act: -0.0000

Data Index: 1406667 (The Pile)

Max Activating Token Index: 264

Text #14

Max Range: 5.0445. Min Range: -5.0445

Max Act: 3.3551. Min Act: -0.0000

Data Index: 1588477 (The Pile)

Max Activating Token Index: 28

Text #15

Max Range: 5.0445. Min Range: -5.0445

Max Act: 3.4888. Min Act: -0.0000

Data Index: 1517457 (The Pile)

Max Activating Token Index: 380

Text #16

Max Range: 5.0445. Min Range: -5.0445

Max Act: 3.4710. Min Act: -0.0000

Data Index: 1406476 (The Pile)

Max Activating Token Index: 314

Text #17

Max Range: 5.0445. Min Range: -5.0445

Max Act: 3.6079. Min Act: -0.0000

Data Index: 931307 (The Pile)

Max Activating Token Index: 215

Text #18

Max Range: 5.0445. Min Range: -5.0445

Max Act: 3.4085. Min Act: -0.0000

Data Index: 453018 (The Pile)

Max Activating Token Index: 622

Text #19

Max Range: 5.0445. Min Range: -5.0445

Max Act: 3.4418. Min Act: -0.0000

Data Index: 1219448 (The Pile)

Max Activating Token Index: 95