Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4028 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1480170 (The Pile)

Max Activating Token Index: 129

Text #1

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.3224. Min Act: -0.0000

Data Index: 1273294 (The Pile)

Max Activating Token Index: 685

Text #2

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.3131. Min Act: -0.0000

Data Index: 930386 (The Pile)

Max Activating Token Index: 947

Text #3

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1339313 (The Pile)

Max Activating Token Index: 568

Text #4

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2649. Min Act: -0.0000

Data Index: 759069 (The Pile)

Max Activating Token Index: 809

Text #5

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2936. Min Act: -0.0000

Data Index: 879781 (The Pile)

Max Activating Token Index: 66

Text #6

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2686. Min Act: -0.0000

Data Index: 1709880 (The Pile)

Max Activating Token Index: 949

Text #7

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2491. Min Act: -0.0000

Data Index: 873742 (The Pile)

Max Activating Token Index: 779

Text #8

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2496. Min Act: -0.0000

Data Index: 1672066 (The Pile)

Max Activating Token Index: 988

Text #9

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2614. Min Act: -0.0000

Data Index: 1157167 (The Pile)

Max Activating Token Index: 693

Text #10

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2433. Min Act: -0.0000

Data Index: 315623 (The Pile)

Max Activating Token Index: 370

Text #11

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2509. Min Act: -0.0000

Data Index: 564514 (The Pile)

Max Activating Token Index: 594

Text #12

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2452. Min Act: -0.0000

Data Index: 1772095 (The Pile)

Max Activating Token Index: 33

Text #13

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1503904 (The Pile)

Max Activating Token Index: 890

Text #14

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2354. Min Act: -0.0000

Data Index: 1639851 (The Pile)

Max Activating Token Index: 479

Text #15

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2315. Min Act: -0.0000

Data Index: 1995809 (The Pile)

Max Activating Token Index: 970

Text #16

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2355. Min Act: -0.0000

Data Index: 8322 (The Pile)

Max Activating Token Index: 680

Text #17

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2392. Min Act: -0.0000

Data Index: 1795538 (The Pile)

Max Activating Token Index: 844

Text #18

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1992618 (The Pile)

Max Activating Token Index: 352

Text #19

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2315. Min Act: -0.0000

Data Index: 1591328 (The Pile)

Max Activating Token Index: 348