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

Dataset: The Pile

Neuron 1744 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: 0.9441. Min Range: -0.9441

Max Act: 0.9441. Min Act: -0.0000

Data Index: 1598408 (The Pile)

Max Activating Token Index: 469

Text #1

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8697. Min Act: -0.0000

Data Index: 1351676 (The Pile)

Max Activating Token Index: 968

Text #2

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8419. Min Act: -0.0000

Data Index: 1631040 (The Pile)

Max Activating Token Index: 660

Text #3

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8356. Min Act: -0.0000

Data Index: 820616 (The Pile)

Max Activating Token Index: 234

Text #4

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1383634 (The Pile)

Max Activating Token Index: 198

Text #5

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1924026 (The Pile)

Max Activating Token Index: 1011

Text #6

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.7726. Min Act: -0.0000

Data Index: 63412 (The Pile)

Max Activating Token Index: 872

Text #7

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.7476. Min Act: -0.0000

Data Index: 1761077 (The Pile)

Max Activating Token Index: 696

Text #8

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.7540. Min Act: -0.0000

Data Index: 4467 (The Pile)

Max Activating Token Index: 576

Text #9

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.7303. Min Act: -0.0000

Data Index: 1100139 (The Pile)

Max Activating Token Index: 287

Text #10

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1706306 (The Pile)

Max Activating Token Index: 136

Text #11

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.6770. Min Act: -0.0000

Data Index: 1526355 (The Pile)

Max Activating Token Index: 882

Text #12

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.7219. Min Act: -0.0000

Data Index: 83881 (The Pile)

Max Activating Token Index: 781

Text #13

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.7652. Min Act: -0.0000

Data Index: 677822 (The Pile)

Max Activating Token Index: 680

Text #14

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1744139 (The Pile)

Max Activating Token Index: 176

Text #15

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.7139. Min Act: -0.0000

Data Index: 670361 (The Pile)

Max Activating Token Index: 551

Text #16

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.6603. Min Act: -0.0000

Data Index: 1197436 (The Pile)

Max Activating Token Index: 553

Text #17

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.6823. Min Act: -0.0000

Data Index: 1904791 (The Pile)

Max Activating Token Index: 1000

Text #18

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.6727. Min Act: -0.0000

Data Index: 999059 (The Pile)

Max Activating Token Index: 378

Text #19

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.6458. Min Act: -0.0000

Data Index: 292444 (The Pile)

Max Activating Token Index: 832