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

Dataset: The Pile

Neuron 3892 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: 1.6034. Min Range: -1.6034

Max Act: 1.5318. Min Act: -0.0000

Data Index: 261991 (The Pile)

Max Activating Token Index: 151

Text #1

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.6034. Min Act: -0.0000

Data Index: 1193065 (The Pile)

Max Activating Token Index: 184

Text #2

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.4408. Min Act: -0.0000

Data Index: 681606 (The Pile)

Max Activating Token Index: 862

Text #3

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.3529. Min Act: -0.0000

Data Index: 1074955 (The Pile)

Max Activating Token Index: 209

Text #4

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.2752. Min Act: -0.0000

Data Index: 1314557 (The Pile)

Max Activating Token Index: 294

Text #5

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.1862. Min Act: -0.0000

Data Index: 1375848 (The Pile)

Max Activating Token Index: 942

Text #6

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.3424. Min Act: -0.0000

Data Index: 1342258 (The Pile)

Max Activating Token Index: 483

Text #7

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.1567. Min Act: -0.0000

Data Index: 1020738 (The Pile)

Max Activating Token Index: 940

Text #8

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.4021. Min Act: -0.0000

Data Index: 38204 (The Pile)

Max Activating Token Index: 626

Text #9

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.2124. Min Act: -0.0000

Data Index: 1144577 (The Pile)

Max Activating Token Index: 398

Text #10

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.3799. Min Act: -0.0000

Data Index: 1309428 (The Pile)

Max Activating Token Index: 75

Text #11

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.3269. Min Act: -0.0000

Data Index: 1080725 (The Pile)

Max Activating Token Index: 157

Text #12

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.2777. Min Act: -0.0000

Data Index: 355223 (The Pile)

Max Activating Token Index: 676

Text #13

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.2595. Min Act: -0.0000

Data Index: 1901574 (The Pile)

Max Activating Token Index: 575

Text #14

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.3189. Min Act: -0.0000

Data Index: 1424935 (The Pile)

Max Activating Token Index: 115

Text #15

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.2446. Min Act: -0.0000

Data Index: 1243848 (The Pile)

Max Activating Token Index: 208

Text #16

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.2675. Min Act: -0.0000

Data Index: 1422953 (The Pile)

Max Activating Token Index: 812

Text #17

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.2918. Min Act: -0.0000

Data Index: 1274582 (The Pile)

Max Activating Token Index: 600

Text #18

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.2148. Min Act: -0.0000

Data Index: 74422 (The Pile)

Max Activating Token Index: 339

Text #19

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.0550. Min Act: -0.0000

Data Index: 1286900 (The Pile)

Max Activating Token Index: 782