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

Dataset: The Pile

Neuron 1966 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: 3.7413. Min Range: -3.7413

Max Act: 3.7413. Min Act: -0.0000

Data Index: 1588974 (The Pile)

Max Activating Token Index: 372

Text #1

Max Range: 3.7413. Min Range: -3.7413

Max Act: 3.7090. Min Act: -0.0000

Data Index: 18905 (The Pile)

Max Activating Token Index: 411

Text #2

Max Range: 3.7413. Min Range: -3.7413

Max Act: 3.5355. Min Act: -0.0000

Data Index: 1208329 (The Pile)

Max Activating Token Index: 256

Text #3

Max Range: 3.7413. Min Range: -3.7413

Max Act: 3.6226. Min Act: -0.0000

Data Index: 387974 (The Pile)

Max Activating Token Index: 501

Text #4

Max Range: 3.7413. Min Range: -3.7413

Max Act: 3.6191. Min Act: -0.0000

Data Index: 864899 (The Pile)

Max Activating Token Index: 617

Text #5

Max Range: 3.7413. Min Range: -3.7413

Max Act: 3.4816. Min Act: -0.0000

Data Index: 350006 (The Pile)

Max Activating Token Index: 464

Text #6

Max Range: 3.7413. Min Range: -3.7413

Max Act: 3.2849. Min Act: -0.0000

Data Index: 1116935 (The Pile)

Max Activating Token Index: 209

Text #7

Max Range: 3.7413. Min Range: -3.7413

Max Act: 3.2591. Min Act: -0.0000

Data Index: 1080852 (The Pile)

Max Activating Token Index: 86

Text #8

Max Range: 3.7413. Min Range: -3.7413

Max Act: 3.2671. Min Act: -0.0000

Data Index: 645636 (The Pile)

Max Activating Token Index: 740

Text #9

Max Range: 3.7413. Min Range: -3.7413

Max Act: 3.4067. Min Act: -0.0000

Data Index: 1589669 (The Pile)

Max Activating Token Index: 869

Text #10

Max Range: 3.7413. Min Range: -3.7413

Max Act: 3.2496. Min Act: -0.0000

Data Index: 785602 (The Pile)

Max Activating Token Index: 905

Text #11

Max Range: 3.7413. Min Range: -3.7413

Max Act: 3.4057. Min Act: -0.0000

Data Index: 1698989 (The Pile)

Max Activating Token Index: 821

Text #12

Max Range: 3.7413. Min Range: -3.7413

Max Act: 3.3639. Min Act: -0.0000

Data Index: 1549236 (The Pile)

Max Activating Token Index: 444

Text #13

Max Range: 3.7413. Min Range: -3.7413

Max Act: 3.3750. Min Act: -0.0000

Data Index: 1176901 (The Pile)

Max Activating Token Index: 845

Text #14

Max Range: 3.7413. Min Range: -3.7413

Max Act: 3.3482. Min Act: -0.0000

Data Index: 620302 (The Pile)

Max Activating Token Index: 157

Text #15

Max Range: 3.7413. Min Range: -3.7413

Max Act: 3.3430. Min Act: -0.0000

Data Index: 1149430 (The Pile)

Max Activating Token Index: 346

Text #16

Max Range: 3.7413. Min Range: -3.7413

Max Act: 3.3159. Min Act: -0.0000

Data Index: 316169 (The Pile)

Max Activating Token Index: 758

Text #17

Max Range: 3.7413. Min Range: -3.7413

Max Act: 3.1431. Min Act: -0.0000

Data Index: 920640 (The Pile)

Max Activating Token Index: 90

Text #18

Max Range: 3.7413. Min Range: -3.7413

Max Act: 3.3029. Min Act: -0.0000

Data Index: 1427992 (The Pile)

Max Activating Token Index: 65

Text #19

Max Range: 3.7413. Min Range: -3.7413

Max Act: 3.2924. Min Act: -0.0000

Data Index: 232601 (The Pile)

Max Activating Token Index: 25