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

Dataset: The Pile

Neuron 2546 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: 0.4548. Min Range: -0.4548

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1918754 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1687870 (The Pile)

Max Activating Token Index: 271

Text #2

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.3806. Min Act: -0.0000

Data Index: 260750 (The Pile)

Max Activating Token Index: 174

Text #3

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.3594. Min Act: -0.0000

Data Index: 979937 (The Pile)

Max Activating Token Index: 375

Text #4

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.3184. Min Act: -0.0000

Data Index: 927193 (The Pile)

Max Activating Token Index: 77

Text #5

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.2807. Min Act: -0.0000

Data Index: 1523723 (The Pile)

Max Activating Token Index: 810

Text #6

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.2677. Min Act: -0.0000

Data Index: 320424 (The Pile)

Max Activating Token Index: 806

Text #7

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.2792. Min Act: -0.0000

Data Index: 1964524 (The Pile)

Max Activating Token Index: 153

Text #8

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.3001. Min Act: -0.0000

Data Index: 1302647 (The Pile)

Max Activating Token Index: 274

Text #9

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.3001. Min Act: -0.0000

Data Index: 269157 (The Pile)

Max Activating Token Index: 738

Text #10

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1557503 (The Pile)

Max Activating Token Index: 425

Text #11

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.2982. Min Act: -0.0000

Data Index: 1794345 (The Pile)

Max Activating Token Index: 886

Text #12

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.2704. Min Act: -0.0000

Data Index: 899987 (The Pile)

Max Activating Token Index: 403

Text #13

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.2539. Min Act: -0.0000

Data Index: 1137931 (The Pile)

Max Activating Token Index: 445

Text #14

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.2736. Min Act: -0.0000

Data Index: 781759 (The Pile)

Max Activating Token Index: 886

Text #15

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.2795. Min Act: -0.0000

Data Index: 375067 (The Pile)

Max Activating Token Index: 182

Text #16

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.2513. Min Act: -0.0000

Data Index: 481329 (The Pile)

Max Activating Token Index: 582

Text #17

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1364248 (The Pile)

Max Activating Token Index: 274

Text #18

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.2646. Min Act: -0.0000

Data Index: 1697381 (The Pile)

Max Activating Token Index: 126

Text #19

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1661096 (The Pile)

Max Activating Token Index: 465