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

Dataset: The Pile

Neuron 2357 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.4572. Min Act: -0.0000

Data Index: 352008 (The Pile)

Max Activating Token Index: 862

Text #1

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.3820. Min Act: -0.0000

Data Index: 1016330 (The Pile)

Max Activating Token Index: 696

Text #2

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.2949. Min Act: -0.0000

Data Index: 1332393 (The Pile)

Max Activating Token Index: 292

Text #3

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.1099. Min Act: -0.0000

Data Index: 8134 (The Pile)

Max Activating Token Index: 176

Text #4

Max Range: 3.4572. Min Range: -3.4572

Max Act: 2.9705. Min Act: -0.0000

Data Index: 101541 (The Pile)

Max Activating Token Index: 858

Text #5

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.1441. Min Act: -0.0000

Data Index: 460624 (The Pile)

Max Activating Token Index: 304

Text #6

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.1438. Min Act: -0.0000

Data Index: 234323 (The Pile)

Max Activating Token Index: 356

Text #7

Max Range: 3.4572. Min Range: -3.4572

Max Act: 2.8792. Min Act: -0.0000

Data Index: 1806261 (The Pile)

Max Activating Token Index: 906

Text #8

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.0251. Min Act: -0.0000

Data Index: 812213 (The Pile)

Max Activating Token Index: 897

Text #9

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.3033. Min Act: -0.0000

Data Index: 200151 (The Pile)

Max Activating Token Index: 294

Text #10

Max Range: 3.4572. Min Range: -3.4572

Max Act: 2.7299. Min Act: -0.0000

Data Index: 72835 (The Pile)

Max Activating Token Index: 222

Text #11

Max Range: 3.4572. Min Range: -3.4572

Max Act: 2.8583. Min Act: -0.0000

Data Index: 935382 (The Pile)

Max Activating Token Index: 450

Text #12

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.1171. Min Act: -0.0000

Data Index: 713863 (The Pile)

Max Activating Token Index: 665

Text #13

Max Range: 3.4572. Min Range: -3.4572

Max Act: 2.9491. Min Act: -0.0000

Data Index: 566130 (The Pile)

Max Activating Token Index: 463

Text #14

Max Range: 3.4572. Min Range: -3.4572

Max Act: 2.8947. Min Act: -0.0000

Data Index: 937343 (The Pile)

Max Activating Token Index: 482

Text #15

Max Range: 3.4572. Min Range: -3.4572

Max Act: 2.9661. Min Act: -0.0000

Data Index: 1958411 (The Pile)

Max Activating Token Index: 601

Text #16

Max Range: 3.4572. Min Range: -3.4572

Max Act: 2.6551. Min Act: -0.0000

Data Index: 140438 (The Pile)

Max Activating Token Index: 488

Text #17

Max Range: 3.4572. Min Range: -3.4572

Max Act: 2.7505. Min Act: -0.0000

Data Index: 1697097 (The Pile)

Max Activating Token Index: 580

Text #18

Max Range: 3.4572. Min Range: -3.4572

Max Act: 2.5790. Min Act: -0.0000

Data Index: 869997 (The Pile)

Max Activating Token Index: 723

Text #19

Max Range: 3.4572. Min Range: -3.4572

Max Act: 2.7124. Min Act: -0.0000

Data Index: 1388734 (The Pile)

Max Activating Token Index: 611