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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1749 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1312. Min Range: -1.1312

Max Act: 1.1312. Min Act: -0.0000

Data Index: 1257441 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 1.1312. Min Range: -1.1312

Max Act: 1.0107. Min Act: -0.0000

Data Index: 808317 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 1.1312. Min Range: -1.1312

Max Act: 1.0278. Min Act: -0.0000

Data Index: 697421 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 1.1312. Min Range: -1.1312

Max Act: 1.0526. Min Act: -0.0000

Data Index: 1482735 (Python Code)

Max Activating Token Index: 720

Text #4

Max Range: 1.1312. Min Range: -1.1312

Max Act: 0.9374. Min Act: -0.0000

Data Index: 472616 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 1.1312. Min Range: -1.1312

Max Act: 0.9823. Min Act: -0.0000

Data Index: 806474 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 1.1312. Min Range: -1.1312

Max Act: 0.9345. Min Act: -0.0000

Data Index: 241038 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 1.1312. Min Range: -1.1312

Max Act: 0.9350. Min Act: -0.0000

Data Index: 927172 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 1.1312. Min Range: -1.1312

Max Act: 0.9562. Min Act: -0.0000

Data Index: 680252 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 1.1312. Min Range: -1.1312

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1111398 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 1.1312. Min Range: -1.1312

Max Act: 0.8831. Min Act: -0.0000

Data Index: 180013 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 1.1312. Min Range: -1.1312

Max Act: 0.9699. Min Act: -0.0000

Data Index: 907940 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 1.1312. Min Range: -1.1312

Max Act: 0.8728. Min Act: -0.0000

Data Index: 909997 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 1.1312. Min Range: -1.1312

Max Act: 0.9017. Min Act: -0.0000

Data Index: 874361 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 1.1312. Min Range: -1.1312

Max Act: 0.8156. Min Act: -0.0000

Data Index: 970964 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 1.1312. Min Range: -1.1312

Max Act: 0.9490. Min Act: -0.0000

Data Index: 1324791 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 1.1312. Min Range: -1.1312

Max Act: 0.8996. Min Act: -0.0000

Data Index: 538564 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 1.1312. Min Range: -1.1312

Max Act: 0.8411. Min Act: -0.0000

Data Index: 114614 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 1.1312. Min Range: -1.1312

Max Act: 0.9068. Min Act: -0.0000

Data Index: 133673 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 1.1312. Min Range: -1.1312

Max Act: 0.9068. Min Act: -0.0000

Data Index: 1508890 (Python Code)

Max Activating Token Index: 577