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

Dataset: The Pile

Neuron 1142 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: 0.2702. Min Range: -0.2702

Max Act: 0.2702. Min Act: -0.0000

Data Index: 380549 (The Pile)

Max Activating Token Index: 819

Text #1

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1853. Min Act: -0.0000

Data Index: 1263383 (The Pile)

Max Activating Token Index: 549

Text #2

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2046. Min Act: -0.0000

Data Index: 619315 (The Pile)

Max Activating Token Index: 3

Text #3

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1757. Min Act: -0.0000

Data Index: 534541 (The Pile)

Max Activating Token Index: 164

Text #4

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1802. Min Act: -0.0000

Data Index: 1201378 (The Pile)

Max Activating Token Index: 383

Text #5

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1559. Min Act: -0.0000

Data Index: 425828 (The Pile)

Max Activating Token Index: 265

Text #6

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1615. Min Act: -0.0000

Data Index: 1987729 (The Pile)

Max Activating Token Index: 1012

Text #7

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1640. Min Act: -0.0000

Data Index: 328892 (The Pile)

Max Activating Token Index: 247

Text #8

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1494. Min Act: -0.0000

Data Index: 1816372 (The Pile)

Max Activating Token Index: 499

Text #9

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1531. Min Act: -0.0000

Data Index: 81349 (The Pile)

Max Activating Token Index: 333

Text #10

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1797. Min Act: -0.0000

Data Index: 1137565 (The Pile)

Max Activating Token Index: 925

Text #11

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1575. Min Act: -0.0000

Data Index: 440462 (The Pile)

Max Activating Token Index: 344

Text #12

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1539. Min Act: -0.0000

Data Index: 837782 (The Pile)

Max Activating Token Index: 218

Text #13

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1530. Min Act: -0.0000

Data Index: 240944 (The Pile)

Max Activating Token Index: 499

Text #14

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1341394 (The Pile)

Max Activating Token Index: 847

Text #15

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1448034 (The Pile)

Max Activating Token Index: 77

Text #16

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1478. Min Act: -0.0000

Data Index: 891589 (The Pile)

Max Activating Token Index: 104

Text #17

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1402. Min Act: -0.0000

Data Index: 1549828 (The Pile)

Max Activating Token Index: 74

Text #18

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1450. Min Act: -0.0000

Data Index: 311979 (The Pile)

Max Activating Token Index: 866

Text #19

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1357. Min Act: -0.0000

Data Index: 964943 (The Pile)

Max Activating Token Index: 279