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

Dataset: The Pile

Neuron 1702 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: 0.8418. Min Range: -0.8418

Max Act: 0.8418. Min Act: -0.0000

Data Index: 988358 (The Pile)

Max Activating Token Index: 436

Text #1

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.7648. Min Act: -0.0000

Data Index: 1320599 (The Pile)

Max Activating Token Index: 443

Text #2

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.7297. Min Act: -0.0000

Data Index: 978821 (The Pile)

Max Activating Token Index: 73

Text #3

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.7088. Min Act: -0.0000

Data Index: 920158 (The Pile)

Max Activating Token Index: 502

Text #4

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.7486. Min Act: -0.0000

Data Index: 1878211 (The Pile)

Max Activating Token Index: 421

Text #5

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6934. Min Act: -0.0000

Data Index: 69236 (The Pile)

Max Activating Token Index: 77

Text #6

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.7084. Min Act: -0.0000

Data Index: 1042981 (The Pile)

Max Activating Token Index: 283

Text #7

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.7116. Min Act: -0.0000

Data Index: 973833 (The Pile)

Max Activating Token Index: 170

Text #8

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6774. Min Act: -0.0000

Data Index: 476897 (The Pile)

Max Activating Token Index: 291

Text #9

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6735. Min Act: -0.0000

Data Index: 587419 (The Pile)

Max Activating Token Index: 239

Text #10

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6849. Min Act: -0.0000

Data Index: 699260 (The Pile)

Max Activating Token Index: 355

Text #11

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6959. Min Act: -0.0000

Data Index: 481459 (The Pile)

Max Activating Token Index: 17

Text #12

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6804. Min Act: -0.0000

Data Index: 238455 (The Pile)

Max Activating Token Index: 247

Text #13

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6554. Min Act: -0.0000

Data Index: 1332731 (The Pile)

Max Activating Token Index: 43

Text #14

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6146. Min Act: -0.0000

Data Index: 1431882 (The Pile)

Max Activating Token Index: 566

Text #15

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6723. Min Act: -0.0000

Data Index: 442250 (The Pile)

Max Activating Token Index: 228

Text #16

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6100. Min Act: -0.0000

Data Index: 81345 (The Pile)

Max Activating Token Index: 174

Text #17

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6417. Min Act: -0.0000

Data Index: 761216 (The Pile)

Max Activating Token Index: 702

Text #18

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6435. Min Act: -0.0000

Data Index: 731570 (The Pile)

Max Activating Token Index: 473

Text #19

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6289. Min Act: -0.0000

Data Index: 828588 (The Pile)

Max Activating Token Index: 327