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

Dataset: The Pile

Neuron 3600 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: 0.4803. Min Range: -0.4803

Max Act: 0.4803. Min Act: -0.0000

Data Index: 1958801 (The Pile)

Max Activating Token Index: 127

Text #1

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.3785. Min Act: -0.0000

Data Index: 829891 (The Pile)

Max Activating Token Index: 448

Text #2

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.3622. Min Act: -0.0000

Data Index: 1454184 (The Pile)

Max Activating Token Index: 546

Text #3

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.3008. Min Act: -0.0000

Data Index: 201597 (The Pile)

Max Activating Token Index: 852

Text #4

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.3120. Min Act: -0.0000

Data Index: 353021 (The Pile)

Max Activating Token Index: 91

Text #5

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.3050. Min Act: -0.0000

Data Index: 1720740 (The Pile)

Max Activating Token Index: 861

Text #6

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.2862. Min Act: -0.0000

Data Index: 1554777 (The Pile)

Max Activating Token Index: 541

Text #7

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.2769. Min Act: -0.0000

Data Index: 1648912 (The Pile)

Max Activating Token Index: 695

Text #8

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.3118. Min Act: -0.0000

Data Index: 383793 (The Pile)

Max Activating Token Index: 38

Text #9

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.2656. Min Act: -0.0000

Data Index: 194248 (The Pile)

Max Activating Token Index: 528

Text #10

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1907646 (The Pile)

Max Activating Token Index: 187

Text #11

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.2657. Min Act: -0.0000

Data Index: 1668822 (The Pile)

Max Activating Token Index: 270

Text #12

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.2650. Min Act: -0.0000

Data Index: 1251264 (The Pile)

Max Activating Token Index: 645

Text #13

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.2678. Min Act: -0.0000

Data Index: 72440 (The Pile)

Max Activating Token Index: 598

Text #14

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.2583. Min Act: -0.0000

Data Index: 855930 (The Pile)

Max Activating Token Index: 651

Text #15

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.2672. Min Act: -0.0000

Data Index: 343795 (The Pile)

Max Activating Token Index: 102

Text #16

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.2568. Min Act: -0.0000

Data Index: 1283353 (The Pile)

Max Activating Token Index: 255

Text #17

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.2198. Min Act: -0.0000

Data Index: 1948687 (The Pile)

Max Activating Token Index: 758

Text #18

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.3110. Min Act: -0.0000

Data Index: 1913001 (The Pile)

Max Activating Token Index: 1007

Text #19

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.2840. Min Act: -0.0000

Data Index: 1140025 (The Pile)

Max Activating Token Index: 714