Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2811 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1461410 (Python Code)

Max Activating Token Index: 451

Text #1

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0461. Min Act: -0.0002

Data Index: 491803 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0452. Min Act: -0.0002

Data Index: 658465 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0447. Min Act: -0.0002

Data Index: 88132 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1558369 (Python Code)

Max Activating Token Index: 421

Text #5

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0439. Min Act: -0.0002

Data Index: 798616 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1204370 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0432. Min Act: -0.0002

Data Index: 844593 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1468396 (Python Code)

Max Activating Token Index: 93

Text #9

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0398. Min Act: -0.0002

Data Index: 791716 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0396. Min Act: -0.0002

Data Index: 529670 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1001844 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0396. Min Act: -0.0002

Data Index: 228848 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1491522 (Python Code)

Max Activating Token Index: 348

Text #14

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1341046 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0392. Min Act: -0.0002

Data Index: 311528 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1076352 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0388. Min Act: -0.0002

Data Index: 542673 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0385. Min Act: -0.0002

Data Index: 740702 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0398. Min Act: -0.0002

Data Index: 447365 (C4 (Web Text))

Max Activating Token Index: 835