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

Dataset: The Pile

Neuron 1684 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: 1.5510. Min Range: -1.5510

Max Act: 1.5510. Min Act: -0.0000

Data Index: 1893287 (The Pile)

Max Activating Token Index: 50

Text #1

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2648. Min Act: -0.0000

Data Index: 1329081 (The Pile)

Max Activating Token Index: 806

Text #2

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.1151. Min Act: -0.0000

Data Index: 717393 (The Pile)

Max Activating Token Index: 1005

Text #3

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.1350. Min Act: -0.0000

Data Index: 148427 (The Pile)

Max Activating Token Index: 280

Text #4

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.1175. Min Act: -0.0000

Data Index: 1230271 (The Pile)

Max Activating Token Index: 225

Text #5

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.0900. Min Act: -0.0000

Data Index: 638145 (The Pile)

Max Activating Token Index: 713

Text #6

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.0648. Min Act: -0.0000

Data Index: 673654 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.0891. Min Act: -0.0000

Data Index: 1373612 (The Pile)

Max Activating Token Index: 183

Text #8

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.1052. Min Act: -0.0000

Data Index: 249824 (The Pile)

Max Activating Token Index: 729

Text #9

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.0284. Min Act: -0.0000

Data Index: 412094 (The Pile)

Max Activating Token Index: 313

Text #10

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.0824. Min Act: -0.0000

Data Index: 1523085 (The Pile)

Max Activating Token Index: 780

Text #11

Max Range: 1.5510. Min Range: -1.5510

Max Act: 0.9830. Min Act: -0.0000

Data Index: 1579492 (The Pile)

Max Activating Token Index: 667

Text #12

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.0099. Min Act: -0.0000

Data Index: 473852 (The Pile)

Max Activating Token Index: 138

Text #13

Max Range: 1.5510. Min Range: -1.5510

Max Act: 0.9887. Min Act: -0.0000

Data Index: 1627191 (The Pile)

Max Activating Token Index: 220

Text #14

Max Range: 1.5510. Min Range: -1.5510

Max Act: 0.9837. Min Act: -0.0000

Data Index: 689460 (The Pile)

Max Activating Token Index: 184

Text #15

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.0068. Min Act: -0.0000

Data Index: 1059300 (The Pile)

Max Activating Token Index: 147

Text #16

Max Range: 1.5510. Min Range: -1.5510

Max Act: 0.9434. Min Act: -0.0000

Data Index: 1241048 (The Pile)

Max Activating Token Index: 365

Text #17

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.0182. Min Act: -0.0000

Data Index: 773324 (The Pile)

Max Activating Token Index: 628

Text #18

Max Range: 1.5510. Min Range: -1.5510

Max Act: 0.9269. Min Act: -0.0000

Data Index: 1812820 (The Pile)

Max Activating Token Index: 62

Text #19

Max Range: 1.5510. Min Range: -1.5510

Max Act: 0.9545. Min Act: -0.0000

Data Index: 1196373 (The Pile)

Max Activating Token Index: 335