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

Dataset: The Pile

Neuron 4220 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1172. Min Range: -1.1172

Max Act: 1.1172. Min Act: -0.0000

Data Index: 1669628 (The Pile)

Max Activating Token Index: 469

Text #1

Max Range: 1.1172. Min Range: -1.1172

Max Act: 1.0340. Min Act: -0.0000

Data Index: 1377625 (The Pile)

Max Activating Token Index: 208

Text #2

Max Range: 1.1172. Min Range: -1.1172

Max Act: 1.0435. Min Act: -0.0000

Data Index: 453975 (The Pile)

Max Activating Token Index: 227

Text #3

Max Range: 1.1172. Min Range: -1.1172

Max Act: 1.0198. Min Act: -0.0000

Data Index: 1822073 (The Pile)

Max Activating Token Index: 469

Text #4

Max Range: 1.1172. Min Range: -1.1172

Max Act: 1.0112. Min Act: -0.0000

Data Index: 1041381 (The Pile)

Max Activating Token Index: 669

Text #5

Max Range: 1.1172. Min Range: -1.1172

Max Act: 1.0121. Min Act: -0.0000

Data Index: 1263910 (The Pile)

Max Activating Token Index: 245

Text #6

Max Range: 1.1172. Min Range: -1.1172

Max Act: 1.0378. Min Act: -0.0000

Data Index: 216589 (The Pile)

Max Activating Token Index: 1009

Text #7

Max Range: 1.1172. Min Range: -1.1172

Max Act: 1.0146. Min Act: -0.0000

Data Index: 343955 (The Pile)

Max Activating Token Index: 743

Text #8

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.9680. Min Act: -0.0000

Data Index: 677926 (The Pile)

Max Activating Token Index: 130

Text #9

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.9711. Min Act: -0.0000

Data Index: 1138565 (The Pile)

Max Activating Token Index: 237

Text #10

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1209964 (The Pile)

Max Activating Token Index: 461

Text #11

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.9282. Min Act: -0.0000

Data Index: 1519733 (The Pile)

Max Activating Token Index: 712

Text #12

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.8442. Min Act: -0.0000

Data Index: 1565990 (The Pile)

Max Activating Token Index: 157

Text #13

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.9122. Min Act: -0.0000

Data Index: 490665 (The Pile)

Max Activating Token Index: 967

Text #14

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.8586. Min Act: -0.0000

Data Index: 763483 (The Pile)

Max Activating Token Index: 270

Text #15

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.8530. Min Act: -0.0000

Data Index: 955722 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1299593 (The Pile)

Max Activating Token Index: 641

Text #17

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.9069. Min Act: -0.0000

Data Index: 868305 (The Pile)

Max Activating Token Index: 907

Text #18

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.8775. Min Act: -0.0000

Data Index: 462300 (The Pile)

Max Activating Token Index: 970

Text #19

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.8115. Min Act: -0.0000

Data Index: 586365 (The Pile)

Max Activating Token Index: 121