Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1860 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3689. Min Act: -0.0000

Data Index: 1483117 (The Pile)

Max Activating Token Index: 720

Text #1

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3070. Min Act: -0.0000

Data Index: 1722561 (The Pile)

Max Activating Token Index: 701

Text #2

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3156. Min Act: -0.0000

Data Index: 1328782 (The Pile)

Max Activating Token Index: 699

Text #3

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1783936 (The Pile)

Max Activating Token Index: 332

Text #4

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3334. Min Act: -0.0000

Data Index: 866006 (The Pile)

Max Activating Token Index: 461

Text #5

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1289831 (The Pile)

Max Activating Token Index: 99

Text #6

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3327. Min Act: -0.0000

Data Index: 1727810 (The Pile)

Max Activating Token Index: 520

Text #7

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3266. Min Act: -0.0000

Data Index: 713859 (The Pile)

Max Activating Token Index: 637

Text #8

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3370. Min Act: -0.0000

Data Index: 185702 (The Pile)

Max Activating Token Index: 698

Text #9

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3409. Min Act: -0.0000

Data Index: 1058980 (The Pile)

Max Activating Token Index: 301

Text #10

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1157630 (The Pile)

Max Activating Token Index: 29

Text #11

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3278. Min Act: -0.0000

Data Index: 469205 (The Pile)

Max Activating Token Index: 399

Text #12

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3033. Min Act: -0.0000

Data Index: 728493 (The Pile)

Max Activating Token Index: 144

Text #13

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3242. Min Act: -0.0000

Data Index: 928510 (The Pile)

Max Activating Token Index: 397

Text #14

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3131. Min Act: -0.0000

Data Index: 812453 (The Pile)

Max Activating Token Index: 343

Text #15

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3181. Min Act: -0.0000

Data Index: 907067 (The Pile)

Max Activating Token Index: 469

Text #16

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3051. Min Act: -0.0000

Data Index: 911738 (The Pile)

Max Activating Token Index: 321

Text #17

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3009. Min Act: -0.0000

Data Index: 1102627 (The Pile)

Max Activating Token Index: 546

Text #18

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3063. Min Act: -0.0000

Data Index: 1974131 (The Pile)

Max Activating Token Index: 709

Text #19

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2886. Min Act: -0.0000

Data Index: 237433 (The Pile)

Max Activating Token Index: 264