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

Dataset: The Pile

Neuron 1433 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: 3.8288. Min Range: -3.8288

Max Act: 3.8288. Min Act: -0.0000

Data Index: 147680 (The Pile)

Max Activating Token Index: 922

Text #1

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.3177. Min Act: -0.0000

Data Index: 1431388 (The Pile)

Max Activating Token Index: 41

Text #2

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.1553. Min Act: -0.0000

Data Index: 1427998 (The Pile)

Max Activating Token Index: 645

Text #3

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.1133. Min Act: -0.0000

Data Index: 1442615 (The Pile)

Max Activating Token Index: 83

Text #4

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.1666. Min Act: -0.0000

Data Index: 31174 (The Pile)

Max Activating Token Index: 49

Text #5

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.1182. Min Act: -0.0000

Data Index: 367267 (The Pile)

Max Activating Token Index: 141

Text #6

Max Range: 3.8288. Min Range: -3.8288

Max Act: 2.8847. Min Act: -0.0000

Data Index: 525283 (The Pile)

Max Activating Token Index: 1015

Text #7

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.4274. Min Act: -0.0000

Data Index: 243176 (The Pile)

Max Activating Token Index: 774

Text #8

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.0023. Min Act: -0.0000

Data Index: 1573365 (The Pile)

Max Activating Token Index: 228

Text #9

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.2127. Min Act: -0.0000

Data Index: 1271871 (The Pile)

Max Activating Token Index: 230

Text #10

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.0945. Min Act: -0.0000

Data Index: 300966 (The Pile)

Max Activating Token Index: 455

Text #11

Max Range: 3.8288. Min Range: -3.8288

Max Act: 2.8242. Min Act: -0.0000

Data Index: 1044441 (The Pile)

Max Activating Token Index: 630

Text #12

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.0686. Min Act: -0.0000

Data Index: 820341 (The Pile)

Max Activating Token Index: 48

Text #13

Max Range: 3.8288. Min Range: -3.8288

Max Act: 2.8185. Min Act: -0.0000

Data Index: 285793 (The Pile)

Max Activating Token Index: 519

Text #14

Max Range: 3.8288. Min Range: -3.8288

Max Act: 2.7341. Min Act: -0.0000

Data Index: 1392829 (The Pile)

Max Activating Token Index: 803

Text #15

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.2040. Min Act: -0.0000

Data Index: 1751904 (The Pile)

Max Activating Token Index: 49

Text #16

Max Range: 3.8288. Min Range: -3.8288

Max Act: 2.8713. Min Act: -0.0000

Data Index: 32974 (The Pile)

Max Activating Token Index: 81

Text #17

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.1082. Min Act: -0.0000

Data Index: 1554314 (The Pile)

Max Activating Token Index: 49

Text #18

Max Range: 3.8288. Min Range: -3.8288

Max Act: 2.8624. Min Act: -0.0000

Data Index: 910294 (The Pile)

Max Activating Token Index: 786

Text #19

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.1154. Min Act: -0.0000

Data Index: 763371 (The Pile)

Max Activating Token Index: 412