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

Dataset: The Pile

Neuron 3811 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: 0.3437. Min Range: -0.3437

Max Act: 0.2937. Min Act: -0.0000

Data Index: 1909503 (The Pile)

Max Activating Token Index: 403

Text #1

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.2900. Min Act: -0.0000

Data Index: 1506767 (The Pile)

Max Activating Token Index: 217

Text #2

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.2863. Min Act: -0.0000

Data Index: 229282 (The Pile)

Max Activating Token Index: 783

Text #3

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.2904. Min Act: -0.0000

Data Index: 1460269 (The Pile)

Max Activating Token Index: 401

Text #4

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1793926 (The Pile)

Max Activating Token Index: 912

Text #5

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.2578. Min Act: -0.0000

Data Index: 1038248 (The Pile)

Max Activating Token Index: 695

Text #6

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.2569. Min Act: -0.0000

Data Index: 1038029 (The Pile)

Max Activating Token Index: 991

Text #7

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.2704. Min Act: -0.0000

Data Index: 1005910 (The Pile)

Max Activating Token Index: 1006

Text #8

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.2652. Min Act: -0.0000

Data Index: 1149777 (The Pile)

Max Activating Token Index: 532

Text #9

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.2616. Min Act: -0.0000

Data Index: 733222 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.2496. Min Act: -0.0000

Data Index: 252485 (The Pile)

Max Activating Token Index: 91

Text #11

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.2490. Min Act: -0.0000

Data Index: 836436 (The Pile)

Max Activating Token Index: 38

Text #12

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.2540. Min Act: -0.0000

Data Index: 1936392 (The Pile)

Max Activating Token Index: 85

Text #13

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.2441. Min Act: -0.0000

Data Index: 682101 (The Pile)

Max Activating Token Index: 235

Text #14

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.2417. Min Act: -0.0000

Data Index: 779160 (The Pile)

Max Activating Token Index: 886

Text #15

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.2509. Min Act: -0.0000

Data Index: 805814 (The Pile)

Max Activating Token Index: 776

Text #16

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.2407. Min Act: -0.0000

Data Index: 557257 (The Pile)

Max Activating Token Index: 600

Text #17

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.2348. Min Act: -0.0000

Data Index: 696759 (The Pile)

Max Activating Token Index: 344

Text #18

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.2342. Min Act: -0.0000

Data Index: 732493 (The Pile)

Max Activating Token Index: 88

Text #19

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1478007 (The Pile)

Max Activating Token Index: 482