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

Dataset: The Pile

Neuron 1105 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1158. Min Range: -1.1158

Max Act: 1.1158. Min Act: -0.0000

Data Index: 1514729 (The Pile)

Max Activating Token Index: 352

Text #1

Max Range: 1.1158. Min Range: -1.1158

Max Act: 1.0504. Min Act: -0.0000

Data Index: 1663293 (The Pile)

Max Activating Token Index: 381

Text #2

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.9728. Min Act: -0.0000

Data Index: 1295979 (The Pile)

Max Activating Token Index: 98

Text #3

Max Range: 1.1158. Min Range: -1.1158

Max Act: 1.0301. Min Act: -0.0000

Data Index: 1697318 (The Pile)

Max Activating Token Index: 49

Text #4

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.9797. Min Act: -0.0000

Data Index: 561223 (The Pile)

Max Activating Token Index: 618

Text #5

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.9769. Min Act: 0.0000

Data Index: 12969 (The Pile)

Max Activating Token Index: 811

Text #6

Max Range: 1.1158. Min Range: -1.1158

Max Act: 1.0614. Min Act: -0.0000

Data Index: 1771718 (The Pile)

Max Activating Token Index: 706

Text #7

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.9262. Min Act: -0.0000

Data Index: 1637270 (The Pile)

Max Activating Token Index: 681

Text #8

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.9976. Min Act: -0.0000

Data Index: 1270990 (The Pile)

Max Activating Token Index: 52

Text #9

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.7901. Min Act: -0.0000

Data Index: 805824 (The Pile)

Max Activating Token Index: 616

Text #10

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.8553. Min Act: -0.0000

Data Index: 863379 (The Pile)

Max Activating Token Index: 374

Text #11

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.7945. Min Act: -0.0000

Data Index: 460669 (The Pile)

Max Activating Token Index: 417

Text #12

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.8525. Min Act: -0.0000

Data Index: 1854802 (The Pile)

Max Activating Token Index: 414

Text #13

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.7687. Min Act: -0.0000

Data Index: 334364 (The Pile)

Max Activating Token Index: 326

Text #14

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.6961. Min Act: -0.0000

Data Index: 430824 (The Pile)

Max Activating Token Index: 965

Text #15

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.7239. Min Act: 0.0000

Data Index: 1528243 (The Pile)

Max Activating Token Index: 301

Text #16

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1913662 (The Pile)

Max Activating Token Index: 591

Text #17

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.7909. Min Act: -0.0000

Data Index: 1787569 (The Pile)

Max Activating Token Index: 53

Text #18

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.7406. Min Act: -0.0000

Data Index: 1025191 (The Pile)

Max Activating Token Index: 915

Text #19

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.8339. Min Act: -0.0000

Data Index: 479187 (The Pile)

Max Activating Token Index: 455