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

Dataset: The Pile

Neuron 3709 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: 0.3077. Min Range: -0.3077

Max Act: 0.2620. Min Act: -0.0000

Data Index: 459322 (The Pile)

Max Activating Token Index: 909

Text #1

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.3077. Min Act: -0.0000

Data Index: 660099 (The Pile)

Max Activating Token Index: 595

Text #2

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2849. Min Act: -0.0000

Data Index: 565376 (The Pile)

Max Activating Token Index: 191

Text #3

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2936. Min Act: -0.0000

Data Index: 383061 (The Pile)

Max Activating Token Index: 264

Text #4

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2681. Min Act: -0.0000

Data Index: 1661681 (The Pile)

Max Activating Token Index: 399

Text #5

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2700. Min Act: -0.0000

Data Index: 834438 (The Pile)

Max Activating Token Index: 784

Text #6

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2659. Min Act: -0.0000

Data Index: 1810301 (The Pile)

Max Activating Token Index: 259

Text #7

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2685. Min Act: -0.0000

Data Index: 961884 (The Pile)

Max Activating Token Index: 586

Text #8

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2504. Min Act: -0.0000

Data Index: 660647 (The Pile)

Max Activating Token Index: 251

Text #9

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2582. Min Act: -0.0000

Data Index: 904308 (The Pile)

Max Activating Token Index: 994

Text #10

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2632. Min Act: -0.0000

Data Index: 562108 (The Pile)

Max Activating Token Index: 386

Text #11

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2529. Min Act: -0.0000

Data Index: 392180 (The Pile)

Max Activating Token Index: 130

Text #12

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2509. Min Act: -0.0000

Data Index: 805701 (The Pile)

Max Activating Token Index: 772

Text #13

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2448. Min Act: -0.0000

Data Index: 1919414 (The Pile)

Max Activating Token Index: 724

Text #14

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2433. Min Act: -0.0000

Data Index: 661630 (The Pile)

Max Activating Token Index: 206

Text #15

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2551. Min Act: -0.0000

Data Index: 90410 (The Pile)

Max Activating Token Index: 735

Text #16

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1492657 (The Pile)

Max Activating Token Index: 214

Text #17

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1932985 (The Pile)

Max Activating Token Index: 316

Text #18

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2514. Min Act: -0.0000

Data Index: 1595045 (The Pile)

Max Activating Token Index: 648

Text #19

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2220. Min Act: -0.0000

Data Index: 1498598 (The Pile)

Max Activating Token Index: 663