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

Dataset: The Pile

Neuron 1540 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.3585. Min Act: -0.0000

Data Index: 202023 (The Pile)

Max Activating Token Index: 696

Text #1

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.3501. Min Act: -0.0000

Data Index: 743791 (The Pile)

Max Activating Token Index: 150

Text #2

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.3015. Min Act: -0.0000

Data Index: 1841628 (The Pile)

Max Activating Token Index: 743

Text #3

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.3391. Min Act: -0.0000

Data Index: 1687656 (The Pile)

Max Activating Token Index: 145

Text #4

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.2224. Min Act: -0.0000

Data Index: 595993 (The Pile)

Max Activating Token Index: 162

Text #5

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.2158. Min Act: -0.0000

Data Index: 1598578 (The Pile)

Max Activating Token Index: 524

Text #6

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.3029. Min Act: -0.0000

Data Index: 906509 (The Pile)

Max Activating Token Index: 814

Text #7

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.2248. Min Act: -0.0000

Data Index: 870331 (The Pile)

Max Activating Token Index: 926

Text #8

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.2038. Min Act: -0.0000

Data Index: 386694 (The Pile)

Max Activating Token Index: 83

Text #9

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.1269. Min Act: -0.0000

Data Index: 1472538 (The Pile)

Max Activating Token Index: 736

Text #10

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.1822. Min Act: -0.0000

Data Index: 795378 (The Pile)

Max Activating Token Index: 85

Text #11

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.1397. Min Act: -0.0000

Data Index: 1737000 (The Pile)

Max Activating Token Index: 140

Text #12

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.1942. Min Act: -0.0000

Data Index: 1560291 (The Pile)

Max Activating Token Index: 12

Text #13

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.1922. Min Act: -0.0000

Data Index: 734222 (The Pile)

Max Activating Token Index: 719

Text #14

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.1181. Min Act: -0.0000

Data Index: 1161638 (The Pile)

Max Activating Token Index: 1006

Text #15

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.1129. Min Act: -0.0000

Data Index: 1912606 (The Pile)

Max Activating Token Index: 197

Text #16

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.0838. Min Act: -0.0000

Data Index: 1359702 (The Pile)

Max Activating Token Index: 693

Text #17

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.1036. Min Act: -0.0000

Data Index: 1187707 (The Pile)

Max Activating Token Index: 969

Text #18

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.1403. Min Act: -0.0000

Data Index: 1013101 (The Pile)

Max Activating Token Index: 263

Text #19

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.0537. Min Act: -0.0000

Data Index: 1925510 (The Pile)

Max Activating Token Index: 280