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

Dataset: The Pile

Neuron 114 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: 0.3580. Min Range: -0.3580

Max Act: 0.3580. Min Act: -0.0000

Data Index: 602805 (The Pile)

Max Activating Token Index: 430

Text #1

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2736. Min Act: -0.0000

Data Index: 971726 (The Pile)

Max Activating Token Index: 967

Text #2

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.3058. Min Act: -0.0000

Data Index: 73243 (The Pile)

Max Activating Token Index: 786

Text #3

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2602. Min Act: -0.0000

Data Index: 581062 (The Pile)

Max Activating Token Index: 65

Text #4

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2591. Min Act: -0.0000

Data Index: 841881 (The Pile)

Max Activating Token Index: 677

Text #5

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2689. Min Act: -0.0000

Data Index: 356165 (The Pile)

Max Activating Token Index: 486

Text #6

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2622. Min Act: -0.0000

Data Index: 150217 (The Pile)

Max Activating Token Index: 860

Text #7

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1251864 (The Pile)

Max Activating Token Index: 1006

Text #8

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2566. Min Act: -0.0000

Data Index: 834664 (The Pile)

Max Activating Token Index: 336

Text #9

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2386. Min Act: -0.0000

Data Index: 1247289 (The Pile)

Max Activating Token Index: 328

Text #10

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2939. Min Act: -0.0000

Data Index: 661758 (The Pile)

Max Activating Token Index: 207

Text #11

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2150. Min Act: -0.0000

Data Index: 361793 (The Pile)

Max Activating Token Index: 776

Text #12

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1767017 (The Pile)

Max Activating Token Index: 514

Text #13

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2309. Min Act: -0.0000

Data Index: 1591851 (The Pile)

Max Activating Token Index: 767

Text #14

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1276333 (The Pile)

Max Activating Token Index: 267

Text #15

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2132. Min Act: -0.0000

Data Index: 1457650 (The Pile)

Max Activating Token Index: 885

Text #16

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2188. Min Act: -0.0000

Data Index: 927358 (The Pile)

Max Activating Token Index: 937

Text #17

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2420. Min Act: -0.0000

Data Index: 651131 (The Pile)

Max Activating Token Index: 929

Text #18

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2258. Min Act: -0.0000

Data Index: 214455 (The Pile)

Max Activating Token Index: 267

Text #19

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2020. Min Act: -0.0000

Data Index: 843752 (The Pile)

Max Activating Token Index: 1005