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

Dataset: The Pile

Neuron 1727 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.3423. Min Act: -0.0000

Data Index: 1410782 (The Pile)

Max Activating Token Index: 270

Text #1

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.3216. Min Act: -0.0000

Data Index: 1161834 (The Pile)

Max Activating Token Index: 261

Text #2

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.3097. Min Act: -0.0000

Data Index: 48683 (The Pile)

Max Activating Token Index: 919

Text #3

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2899. Min Act: -0.0000

Data Index: 104531 (The Pile)

Max Activating Token Index: 286

Text #4

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1818448 (The Pile)

Max Activating Token Index: 607

Text #5

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2882. Min Act: -0.0000

Data Index: 1919028 (The Pile)

Max Activating Token Index: 450

Text #6

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2708. Min Act: 0.0000

Data Index: 853815 (The Pile)

Max Activating Token Index: 303

Text #7

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2605. Min Act: -0.0000

Data Index: 372190 (The Pile)

Max Activating Token Index: 326

Text #8

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2770. Min Act: -0.0000

Data Index: 1871673 (The Pile)

Max Activating Token Index: 659

Text #9

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2681. Min Act: -0.0000

Data Index: 1574096 (The Pile)

Max Activating Token Index: 990

Text #10

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2539. Min Act: 0.0000

Data Index: 1055 (The Pile)

Max Activating Token Index: 342

Text #11

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2456. Min Act: -0.0000

Data Index: 929573 (The Pile)

Max Activating Token Index: 23

Text #12

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2636. Min Act: -0.0000

Data Index: 220791 (The Pile)

Max Activating Token Index: 569

Text #13

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2601. Min Act: -0.0000

Data Index: 597624 (The Pile)

Max Activating Token Index: 123

Text #14

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2409. Min Act: -0.0000

Data Index: 859480 (The Pile)

Max Activating Token Index: 139

Text #15

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2457. Min Act: -0.0000

Data Index: 485096 (The Pile)

Max Activating Token Index: 148

Text #16

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2525. Min Act: -0.0000

Data Index: 345177 (The Pile)

Max Activating Token Index: 348

Text #17

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2319. Min Act: -0.0000

Data Index: 110 (The Pile)

Max Activating Token Index: 154

Text #18

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2405. Min Act: -0.0000

Data Index: 14864 (The Pile)

Max Activating Token Index: 333

Text #19

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1159622 (The Pile)

Max Activating Token Index: 507