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

Dataset: The Pile

Neuron 1351 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: 0.3886. Min Range: -0.3886

Max Act: 0.3886. Min Act: -0.0000

Data Index: 977949 (The Pile)

Max Activating Token Index: 352

Text #1

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3560. Min Act: -0.0000

Data Index: 666797 (The Pile)

Max Activating Token Index: 409

Text #2

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3437. Min Act: -0.0000

Data Index: 629052 (The Pile)

Max Activating Token Index: 788

Text #3

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3167. Min Act: -0.0000

Data Index: 1308725 (The Pile)

Max Activating Token Index: 335

Text #4

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3098. Min Act: -0.0000

Data Index: 1315029 (The Pile)

Max Activating Token Index: 690

Text #5

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2738. Min Act: -0.0000

Data Index: 342358 (The Pile)

Max Activating Token Index: 467

Text #6

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2571. Min Act: -0.0000

Data Index: 1840261 (The Pile)

Max Activating Token Index: 729

Text #7

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2878. Min Act: -0.0000

Data Index: 38730 (The Pile)

Max Activating Token Index: 349

Text #8

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2859. Min Act: -0.0000

Data Index: 1268826 (The Pile)

Max Activating Token Index: 630

Text #9

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2712. Min Act: -0.0000

Data Index: 942284 (The Pile)

Max Activating Token Index: 738

Text #10

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1209177 (The Pile)

Max Activating Token Index: 294

Text #11

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2439. Min Act: -0.0000

Data Index: 1300968 (The Pile)

Max Activating Token Index: 236

Text #12

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2668. Min Act: -0.0000

Data Index: 1201310 (The Pile)

Max Activating Token Index: 533

Text #13

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1847953 (The Pile)

Max Activating Token Index: 926

Text #14

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2307. Min Act: -0.0000

Data Index: 959003 (The Pile)

Max Activating Token Index: 894

Text #15

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2496. Min Act: -0.0000

Data Index: 1149956 (The Pile)

Max Activating Token Index: 412

Text #16

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2715. Min Act: -0.0000

Data Index: 1708417 (The Pile)

Max Activating Token Index: 939

Text #17

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2206. Min Act: -0.0000

Data Index: 1791597 (The Pile)

Max Activating Token Index: 179

Text #18

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2460. Min Act: -0.0000

Data Index: 1377825 (The Pile)

Max Activating Token Index: 692

Text #19

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2123. Min Act: -0.0000

Data Index: 353260 (The Pile)

Max Activating Token Index: 495