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

Dataset: The Pile

Neuron 870 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.4700. Min Act: -0.0000

Data Index: 169739 (The Pile)

Max Activating Token Index: 699

Text #1

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3532. Min Act: -0.0000

Data Index: 448822 (The Pile)

Max Activating Token Index: 698

Text #2

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3357. Min Act: -0.0000

Data Index: 1951893 (The Pile)

Max Activating Token Index: 572

Text #3

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3289. Min Act: -0.0000

Data Index: 450652 (The Pile)

Max Activating Token Index: 222

Text #4

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3136. Min Act: -0.0000

Data Index: 980013 (The Pile)

Max Activating Token Index: 275

Text #5

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1943505 (The Pile)

Max Activating Token Index: 998

Text #6

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2827. Min Act: -0.0000

Data Index: 1942985 (The Pile)

Max Activating Token Index: 795

Text #7

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2796. Min Act: -0.0000

Data Index: 535732 (The Pile)

Max Activating Token Index: 265

Text #8

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2894. Min Act: -0.0000

Data Index: 1171835 (The Pile)

Max Activating Token Index: 649

Text #9

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2693. Min Act: -0.0000

Data Index: 544459 (The Pile)

Max Activating Token Index: 727

Text #10

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2730. Min Act: -0.0000

Data Index: 1816651 (The Pile)

Max Activating Token Index: 716

Text #11

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2475. Min Act: -0.0000

Data Index: 866918 (The Pile)

Max Activating Token Index: 836

Text #12

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2694. Min Act: -0.0000

Data Index: 196085 (The Pile)

Max Activating Token Index: 409

Text #13

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2228. Min Act: -0.0000

Data Index: 1510228 (The Pile)

Max Activating Token Index: 711

Text #14

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2578. Min Act: -0.0000

Data Index: 1091611 (The Pile)

Max Activating Token Index: 717

Text #15

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2486. Min Act: -0.0000

Data Index: 382876 (The Pile)

Max Activating Token Index: 793

Text #16

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2643. Min Act: -0.0000

Data Index: 539640 (The Pile)

Max Activating Token Index: 373

Text #17

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2763. Min Act: -0.0000

Data Index: 157000 (The Pile)

Max Activating Token Index: 566

Text #18

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2562. Min Act: -0.0000

Data Index: 511925 (The Pile)

Max Activating Token Index: 855

Text #19

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2504. Min Act: -0.0000

Data Index: 446157 (The Pile)

Max Activating Token Index: 187