Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 902 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0477. Min Act: -0.0002

Data Index: 93433 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0476. Min Act: -0.0002

Data Index: 87907 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0456. Min Act: -0.0002

Data Index: 274123 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0474. Min Act: -0.0002

Data Index: 511465 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0453. Min Act: -0.0001

Data Index: 1165140 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0448. Min Act: -0.0002

Data Index: 466724 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0453. Min Act: -0.0002

Data Index: 167776 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0440. Min Act: -0.0002

Data Index: 271306 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0432. Min Act: -0.0002

Data Index: 776562 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0453. Min Act: -0.0002

Data Index: 84424 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0446. Min Act: -0.0002

Data Index: 260914 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0438. Min Act: -0.0002

Data Index: 104635 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0441. Min Act: -0.0002

Data Index: 71322 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1050463 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0442. Min Act: -0.0002

Data Index: 292959 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0450. Min Act: -0.0002

Data Index: 90607 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0426. Min Act: -0.0002

Data Index: 786179 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0432. Min Act: -0.0002

Data Index: 389507 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1285052 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1324035 (C4 (Web Text))

Max Activating Token Index: 21