Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3394 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.7559. Min Act: -0.0000

Data Index: 591319 (The Pile)

Max Activating Token Index: 766

Text #1

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.4995. Min Act: 0.0000

Data Index: 733149 (The Pile)

Max Activating Token Index: 650

Text #2

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.4124. Min Act: -0.0000

Data Index: 679901 (The Pile)

Max Activating Token Index: 299

Text #3

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.3921. Min Act: -0.0000

Data Index: 415721 (The Pile)

Max Activating Token Index: 91

Text #4

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.3493. Min Act: -0.0000

Data Index: 1741059 (The Pile)

Max Activating Token Index: 255

Text #5

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.3371. Min Act: -0.0000

Data Index: 759754 (The Pile)

Max Activating Token Index: 500

Text #6

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.3669. Min Act: -0.0000

Data Index: 1692419 (The Pile)

Max Activating Token Index: 336

Text #7

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1628457 (The Pile)

Max Activating Token Index: 842

Text #8

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.2695. Min Act: -0.0000

Data Index: 1876312 (The Pile)

Max Activating Token Index: 185

Text #9

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.2764. Min Act: -0.0000

Data Index: 1027411 (The Pile)

Max Activating Token Index: 180

Text #10

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.2634. Min Act: -0.0000

Data Index: 305737 (The Pile)

Max Activating Token Index: 946

Text #11

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.2610. Min Act: -0.0000

Data Index: 1882999 (The Pile)

Max Activating Token Index: 346

Text #12

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.2610. Min Act: -0.0000

Data Index: 1809028 (The Pile)

Max Activating Token Index: 984

Text #13

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.2659. Min Act: -0.0000

Data Index: 689479 (The Pile)

Max Activating Token Index: 120

Text #14

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.2758. Min Act: -0.0000

Data Index: 710228 (The Pile)

Max Activating Token Index: 610

Text #15

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.2666. Min Act: -0.0000

Data Index: 826431 (The Pile)

Max Activating Token Index: 776

Text #16

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.2377. Min Act: -0.0000

Data Index: 941823 (The Pile)

Max Activating Token Index: 634

Text #17

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.2503. Min Act: -0.0000

Data Index: 873275 (The Pile)

Max Activating Token Index: 197

Text #18

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.2639. Min Act: -0.0000

Data Index: 1618887 (The Pile)

Max Activating Token Index: 601

Text #19

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.2318. Min Act: -0.0000

Data Index: 851349 (The Pile)

Max Activating Token Index: 721