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

Dataset: The Pile

Neuron 3605 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: 1.5197. Min Range: -1.5197

Max Act: 1.5197. Min Act: -0.0000

Data Index: 25770 (The Pile)

Max Activating Token Index: 584

Text #1

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.4051. Min Act: -0.0000

Data Index: 859381 (The Pile)

Max Activating Token Index: 629

Text #2

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.4853. Min Act: -0.0000

Data Index: 699994 (The Pile)

Max Activating Token Index: 417

Text #3

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.4400. Min Act: -0.0000

Data Index: 1410146 (The Pile)

Max Activating Token Index: 322

Text #4

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.3912. Min Act: -0.0000

Data Index: 443104 (The Pile)

Max Activating Token Index: 76

Text #5

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.3198. Min Act: -0.0000

Data Index: 1226816 (The Pile)

Max Activating Token Index: 849

Text #6

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.3874. Min Act: -0.0000

Data Index: 1330025 (The Pile)

Max Activating Token Index: 80

Text #7

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.3841. Min Act: -0.0000

Data Index: 737250 (The Pile)

Max Activating Token Index: 313

Text #8

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.3574. Min Act: -0.0000

Data Index: 284675 (The Pile)

Max Activating Token Index: 350

Text #9

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.3117. Min Act: -0.0000

Data Index: 312773 (The Pile)

Max Activating Token Index: 236

Text #10

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.3176. Min Act: -0.0000

Data Index: 1936502 (The Pile)

Max Activating Token Index: 752

Text #11

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.2285. Min Act: -0.0000

Data Index: 1337432 (The Pile)

Max Activating Token Index: 963

Text #12

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.2958. Min Act: -0.0000

Data Index: 289027 (The Pile)

Max Activating Token Index: 205

Text #13

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.0731. Min Act: -0.0000

Data Index: 1533269 (The Pile)

Max Activating Token Index: 721

Text #14

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.2569. Min Act: -0.0000

Data Index: 8570 (The Pile)

Max Activating Token Index: 37

Text #15

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.1708. Min Act: -0.0000

Data Index: 1151265 (The Pile)

Max Activating Token Index: 126

Text #16

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.1555. Min Act: -0.0000

Data Index: 151024 (The Pile)

Max Activating Token Index: 225

Text #17

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.1573. Min Act: -0.0000

Data Index: 1770076 (The Pile)

Max Activating Token Index: 939

Text #18

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.1469. Min Act: -0.0000

Data Index: 1511212 (The Pile)

Max Activating Token Index: 759

Text #19

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.0446. Min Act: -0.0000

Data Index: 1718052 (The Pile)

Max Activating Token Index: 794