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

Dataset: The Pile

Neuron 614 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.3771. Min Act: 0.0000

Data Index: 927260 (The Pile)

Max Activating Token Index: 881

Text #1

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.1325. Min Act: -0.0000

Data Index: 1197116 (The Pile)

Max Activating Token Index: 787

Text #2

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.0775. Min Act: -0.0000

Data Index: 1250083 (The Pile)

Max Activating Token Index: 244

Text #3

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.1192. Min Act: -0.0000

Data Index: 1113796 (The Pile)

Max Activating Token Index: 404

Text #4

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.9762. Min Act: -0.0000

Data Index: 1890345 (The Pile)

Max Activating Token Index: 1006

Text #5

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.9698. Min Act: 0.0000

Data Index: 793007 (The Pile)

Max Activating Token Index: 433

Text #6

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.9362. Min Act: -0.0000

Data Index: 58138 (The Pile)

Max Activating Token Index: 212

Text #7

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.9640. Min Act: 0.0000

Data Index: 582340 (The Pile)

Max Activating Token Index: 292

Text #8

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.9535. Min Act: -0.0000

Data Index: 791884 (The Pile)

Max Activating Token Index: 862

Text #9

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.9434. Min Act: -0.0000

Data Index: 483367 (The Pile)

Max Activating Token Index: 210

Text #10

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.8845. Min Act: -0.0000

Data Index: 27868 (The Pile)

Max Activating Token Index: 262

Text #11

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.9540. Min Act: -0.0000

Data Index: 1201701 (The Pile)

Max Activating Token Index: 622

Text #12

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.9330. Min Act: 0.0000

Data Index: 1428115 (The Pile)

Max Activating Token Index: 688

Text #13

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.9300. Min Act: -0.0000

Data Index: 633868 (The Pile)

Max Activating Token Index: 722

Text #14

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.8339. Min Act: -0.0000

Data Index: 55128 (The Pile)

Max Activating Token Index: 936

Text #15

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.9319. Min Act: -0.0000

Data Index: 1346185 (The Pile)

Max Activating Token Index: 891

Text #16

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.8766. Min Act: -0.0000

Data Index: 1729196 (The Pile)

Max Activating Token Index: 304

Text #17

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.9690. Min Act: -0.0000

Data Index: 1702438 (The Pile)

Max Activating Token Index: 88

Text #18

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.9129. Min Act: -0.0000

Data Index: 87444 (The Pile)

Max Activating Token Index: 772

Text #19

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.9161. Min Act: 0.0000

Data Index: 1731078 (The Pile)

Max Activating Token Index: 528