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

Dataset: The Pile

Neuron 1261 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1847873 (The Pile)

Max Activating Token Index: 219

Text #1

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.3233. Min Act: -0.0000

Data Index: 1959918 (The Pile)

Max Activating Token Index: 677

Text #2

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2929. Min Act: -0.0000

Data Index: 881401 (The Pile)

Max Activating Token Index: 300

Text #3

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2967. Min Act: -0.0000

Data Index: 1057983 (The Pile)

Max Activating Token Index: 49

Text #4

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1018626 (The Pile)

Max Activating Token Index: 397

Text #5

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2765. Min Act: -0.0000

Data Index: 707684 (The Pile)

Max Activating Token Index: 314

Text #6

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1526833 (The Pile)

Max Activating Token Index: 176

Text #7

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2698. Min Act: -0.0000

Data Index: 14702 (The Pile)

Max Activating Token Index: 937

Text #8

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2778. Min Act: -0.0000

Data Index: 959738 (The Pile)

Max Activating Token Index: 114

Text #9

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2322. Min Act: -0.0000

Data Index: 62853 (The Pile)

Max Activating Token Index: 810

Text #10

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1485564 (The Pile)

Max Activating Token Index: 262

Text #11

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1919756 (The Pile)

Max Activating Token Index: 573

Text #12

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1982685 (The Pile)

Max Activating Token Index: 591

Text #13

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2419. Min Act: -0.0000

Data Index: 1638728 (The Pile)

Max Activating Token Index: 76

Text #14

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2416. Min Act: -0.0000

Data Index: 491896 (The Pile)

Max Activating Token Index: 131

Text #15

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2381. Min Act: -0.0000

Data Index: 656733 (The Pile)

Max Activating Token Index: 881

Text #16

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2434. Min Act: -0.0000

Data Index: 655292 (The Pile)

Max Activating Token Index: 488

Text #17

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2499. Min Act: -0.0000

Data Index: 1920956 (The Pile)

Max Activating Token Index: 604

Text #18

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2419. Min Act: -0.0000

Data Index: 286289 (The Pile)

Max Activating Token Index: 456

Text #19

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1056061 (The Pile)

Max Activating Token Index: 107