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

Dataset: The Pile

Neuron 2880 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.4397. Min Act: -0.0000

Data Index: 1141892 (The Pile)

Max Activating Token Index: 564

Text #1

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.5021. Min Act: -0.0000

Data Index: 1992514 (The Pile)

Max Activating Token Index: 634

Text #2

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.5235. Min Act: -0.0000

Data Index: 308142 (The Pile)

Max Activating Token Index: 756

Text #3

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.1067. Min Act: -0.0000

Data Index: 133104 (The Pile)

Max Activating Token Index: 1017

Text #4

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.2509. Min Act: -0.0000

Data Index: 547210 (The Pile)

Max Activating Token Index: 877

Text #5

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.2708. Min Act: -0.0000

Data Index: 1453317 (The Pile)

Max Activating Token Index: 935

Text #6

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.3459. Min Act: -0.0000

Data Index: 1285236 (The Pile)

Max Activating Token Index: 607

Text #7

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.1385. Min Act: -0.0000

Data Index: 521714 (The Pile)

Max Activating Token Index: 545

Text #8

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.3189. Min Act: -0.0000

Data Index: 1625506 (The Pile)

Max Activating Token Index: 1010

Text #9

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.1584. Min Act: -0.0000

Data Index: 363187 (The Pile)

Max Activating Token Index: 577

Text #10

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.1584. Min Act: -0.0000

Data Index: 1504087 (The Pile)

Max Activating Token Index: 874

Text #11

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.2059. Min Act: -0.0000

Data Index: 511917 (The Pile)

Max Activating Token Index: 442

Text #12

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.2667. Min Act: -0.0000

Data Index: 918592 (The Pile)

Max Activating Token Index: 640

Text #13

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.2321. Min Act: -0.0000

Data Index: 761467 (The Pile)

Max Activating Token Index: 274

Text #14

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.1926. Min Act: -0.0000

Data Index: 987015 (The Pile)

Max Activating Token Index: 835

Text #15

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.2469. Min Act: -0.0000

Data Index: 969666 (The Pile)

Max Activating Token Index: 815

Text #16

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.1178. Min Act: -0.0000

Data Index: 396739 (The Pile)

Max Activating Token Index: 131

Text #17

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.2535. Min Act: -0.0000

Data Index: 311832 (The Pile)

Max Activating Token Index: 696

Text #18

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.1533. Min Act: -0.0000

Data Index: 689053 (The Pile)

Max Activating Token Index: 897

Text #19

Max Range: 1.5235. Min Range: -1.5235

Max Act: 1.0430. Min Act: -0.0000

Data Index: 1258758 (The Pile)

Max Activating Token Index: 521