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

Dataset: The Pile

Neuron 4592 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: 0.6392. Min Range: -0.6392

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1954711 (The Pile)

Max Activating Token Index: 34

Text #1

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.6392. Min Act: -0.0000

Data Index: 625815 (The Pile)

Max Activating Token Index: 752

Text #2

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5847. Min Act: -0.0000

Data Index: 411377 (The Pile)

Max Activating Token Index: 68

Text #3

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.6113. Min Act: -0.0000

Data Index: 410890 (The Pile)

Max Activating Token Index: 16

Text #4

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5908. Min Act: -0.0000

Data Index: 543973 (The Pile)

Max Activating Token Index: 632

Text #5

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.6036. Min Act: -0.0000

Data Index: 1295895 (The Pile)

Max Activating Token Index: 102

Text #6

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1336716 (The Pile)

Max Activating Token Index: 149

Text #7

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5499. Min Act: -0.0000

Data Index: 92300 (The Pile)

Max Activating Token Index: 174

Text #8

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5415. Min Act: -0.0000

Data Index: 301989 (The Pile)

Max Activating Token Index: 213

Text #9

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5396. Min Act: -0.0000

Data Index: 965467 (The Pile)

Max Activating Token Index: 109

Text #10

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5508. Min Act: -0.0000

Data Index: 915354 (The Pile)

Max Activating Token Index: 678

Text #11

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5493. Min Act: -0.0000

Data Index: 999407 (The Pile)

Max Activating Token Index: 259

Text #12

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5710. Min Act: -0.0000

Data Index: 324637 (The Pile)

Max Activating Token Index: 302

Text #13

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5171. Min Act: -0.0000

Data Index: 299084 (The Pile)

Max Activating Token Index: 967

Text #14

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5534. Min Act: -0.0000

Data Index: 749795 (The Pile)

Max Activating Token Index: 10

Text #15

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5329. Min Act: -0.0000

Data Index: 277439 (The Pile)

Max Activating Token Index: 278

Text #16

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1905324 (The Pile)

Max Activating Token Index: 679

Text #17

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1196791 (The Pile)

Max Activating Token Index: 374

Text #18

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5298. Min Act: -0.0000

Data Index: 1120228 (The Pile)

Max Activating Token Index: 926

Text #19

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5305. Min Act: -0.0000

Data Index: 1839570 (The Pile)

Max Activating Token Index: 525