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

Dataset: The Pile

Neuron 4125 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1730. Min Range: -4.1730

Max Act: 4.1730. Min Act: -0.0000

Data Index: 270709 (The Pile)

Max Activating Token Index: 861

Text #1

Max Range: 4.1730. Min Range: -4.1730

Max Act: 3.5962. Min Act: -0.0000

Data Index: 104020 (The Pile)

Max Activating Token Index: 167

Text #2

Max Range: 4.1730. Min Range: -4.1730

Max Act: 3.4335. Min Act: -0.0000

Data Index: 385799 (The Pile)

Max Activating Token Index: 431

Text #3

Max Range: 4.1730. Min Range: -4.1730

Max Act: 3.5671. Min Act: -0.0000

Data Index: 1835336 (The Pile)

Max Activating Token Index: 317

Text #4

Max Range: 4.1730. Min Range: -4.1730

Max Act: 3.2318. Min Act: -0.0000

Data Index: 1996492 (The Pile)

Max Activating Token Index: 919

Text #5

Max Range: 4.1730. Min Range: -4.1730

Max Act: 3.3299. Min Act: -0.0000

Data Index: 1494173 (The Pile)

Max Activating Token Index: 885

Text #6

Max Range: 4.1730. Min Range: -4.1730

Max Act: 3.4938. Min Act: -0.0000

Data Index: 994466 (The Pile)

Max Activating Token Index: 378

Text #7

Max Range: 4.1730. Min Range: -4.1730

Max Act: 3.4863. Min Act: -0.0000

Data Index: 1441028 (The Pile)

Max Activating Token Index: 792

Text #8

Max Range: 4.1730. Min Range: -4.1730

Max Act: 3.6046. Min Act: -0.0000

Data Index: 1274804 (The Pile)

Max Activating Token Index: 780

Text #9

Max Range: 4.1730. Min Range: -4.1730

Max Act: 3.1452. Min Act: -0.0000

Data Index: 299068 (The Pile)

Max Activating Token Index: 515

Text #10

Max Range: 4.1730. Min Range: -4.1730

Max Act: 3.6983. Min Act: -0.0000

Data Index: 1800704 (The Pile)

Max Activating Token Index: 965

Text #11

Max Range: 4.1730. Min Range: -4.1730

Max Act: 3.5178. Min Act: -0.0000

Data Index: 1219521 (The Pile)

Max Activating Token Index: 920

Text #12

Max Range: 4.1730. Min Range: -4.1730

Max Act: 3.1912. Min Act: -0.0000

Data Index: 1089734 (The Pile)

Max Activating Token Index: 147

Text #13

Max Range: 4.1730. Min Range: -4.1730

Max Act: 3.1961. Min Act: -0.0000

Data Index: 1543722 (The Pile)

Max Activating Token Index: 369

Text #14

Max Range: 4.1730. Min Range: -4.1730

Max Act: 3.1753. Min Act: -0.0000

Data Index: 347400 (The Pile)

Max Activating Token Index: 244

Text #15

Max Range: 4.1730. Min Range: -4.1730

Max Act: 3.4593. Min Act: -0.0000

Data Index: 1064396 (The Pile)

Max Activating Token Index: 61

Text #16

Max Range: 4.1730. Min Range: -4.1730

Max Act: 3.3156. Min Act: -0.0000

Data Index: 395840 (The Pile)

Max Activating Token Index: 339

Text #17

Max Range: 4.1730. Min Range: -4.1730

Max Act: 3.3029. Min Act: -0.0000

Data Index: 671121 (The Pile)

Max Activating Token Index: 56

Text #18

Max Range: 4.1730. Min Range: -4.1730

Max Act: 3.3093. Min Act: -0.0000

Data Index: 1323679 (The Pile)

Max Activating Token Index: 499

Text #19

Max Range: 4.1730. Min Range: -4.1730

Max Act: 3.2888. Min Act: -0.0000

Data Index: 1016292 (The Pile)

Max Activating Token Index: 559