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

Dataset: The Pile

Neuron 246 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: 0.5821. Min Range: -0.5821

Max Act: 0.5821. Min Act: -0.0000

Data Index: 766985 (The Pile)

Max Activating Token Index: 256

Text #1

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.5719. Min Act: 0.0000

Data Index: 815917 (The Pile)

Max Activating Token Index: 502

Text #2

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1423568 (The Pile)

Max Activating Token Index: 513

Text #3

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4941. Min Act: -0.0000

Data Index: 340380 (The Pile)

Max Activating Token Index: 261

Text #4

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4249. Min Act: -0.0000

Data Index: 511169 (The Pile)

Max Activating Token Index: 558

Text #5

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4306. Min Act: -0.0000

Data Index: 449416 (The Pile)

Max Activating Token Index: 762

Text #6

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4763. Min Act: -0.0000

Data Index: 1398426 (The Pile)

Max Activating Token Index: 198

Text #7

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4644. Min Act: -0.0000

Data Index: 1419173 (The Pile)

Max Activating Token Index: 959

Text #8

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1297506 (The Pile)

Max Activating Token Index: 856

Text #9

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1392186 (The Pile)

Max Activating Token Index: 64

Text #10

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1808698 (The Pile)

Max Activating Token Index: 574

Text #11

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4687. Min Act: -0.0000

Data Index: 1468646 (The Pile)

Max Activating Token Index: 260

Text #12

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1956501 (The Pile)

Max Activating Token Index: 1007

Text #13

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4530. Min Act: -0.0000

Data Index: 302213 (The Pile)

Max Activating Token Index: 972

Text #14

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4460. Min Act: -0.0000

Data Index: 1139835 (The Pile)

Max Activating Token Index: 17

Text #15

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4539. Min Act: -0.0000

Data Index: 466689 (The Pile)

Max Activating Token Index: 613

Text #16

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4458. Min Act: -0.0000

Data Index: 603005 (The Pile)

Max Activating Token Index: 43

Text #17

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4418. Min Act: 0.0000

Data Index: 1542014 (The Pile)

Max Activating Token Index: 56

Text #18

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4197. Min Act: -0.0000

Data Index: 1035689 (The Pile)

Max Activating Token Index: 298

Text #19

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4333. Min Act: -0.0000

Data Index: 990609 (The Pile)

Max Activating Token Index: 729