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

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

Neuron 2028 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0504. Min Act: -0.0002

Data Index: 19588 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0491. Min Act: -0.0002

Data Index: 175037 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0487. Min Act: -0.0002

Data Index: 608287 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0483. Min Act: -0.0003

Data Index: 554955 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1001436 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0455. Min Act: -0.0002

Data Index: 313760 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0466. Min Act: -0.0003

Data Index: 1294723 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0449. Min Act: -0.0003

Data Index: 357579 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0432. Min Act: -0.0002

Data Index: 452628 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0439. Min Act: -0.0002

Data Index: 502182 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0431. Min Act: -0.0003

Data Index: 483376 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0435. Min Act: -0.0002

Data Index: 145712 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0430. Min Act: -0.0003

Data Index: 1200054 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0421. Min Act: -0.0003

Data Index: 1287906 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0435. Min Act: -0.0003

Data Index: 1032192 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0419. Min Act: -0.0003

Data Index: 158088 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0424. Min Act: -0.0003

Data Index: 1308476 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0424. Min Act: -0.0003

Data Index: 1009003 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0409. Min Act: -0.0003

Data Index: 276556 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0423. Min Act: -0.0003

Data Index: 177650 (C4 (Web Text))

Max Activating Token Index: 108