Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1523 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0525. Min Act: -0.0003

Data Index: 926586 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1068331 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1265834 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0486. Min Act: -0.0003

Data Index: 536463 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0474. Min Act: -0.0003

Data Index: 661086 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0470. Min Act: -0.0003

Data Index: 230956 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0465. Min Act: -0.0003

Data Index: 1249408 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1022555 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0468. Min Act: -0.0004

Data Index: 53911 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0455. Min Act: -0.0003

Data Index: 802568 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0456. Min Act: -0.0004

Data Index: 478255 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0449. Min Act: -0.0002

Data Index: 285510 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0449. Min Act: -0.0003

Data Index: 354634 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1293706 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0430. Min Act: -0.0003

Data Index: 672536 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0444. Min Act: -0.0003

Data Index: 154490 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0453. Min Act: -0.0003

Data Index: 1291443 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0444. Min Act: -0.0003

Data Index: 319480 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0444. Min Act: -0.0003

Data Index: 376439 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0440. Min Act: -0.0003

Data Index: 111145 (C4 (Web Text))

Max Activating Token Index: 961