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

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

Neuron 189 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: 0.0555. Min Range: -0.0555

Max Act: 0.0555. Min Act: -0.0003

Data Index: 1392210 (Python Code)

Max Activating Token Index: 370

Text #1

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0498. Min Act: -0.0003

Data Index: 1521293 (Python Code)

Max Activating Token Index: 427

Text #2

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0487. Min Act: -0.0003

Data Index: 1567360 (Python Code)

Max Activating Token Index: 861

Text #3

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1498634 (Python Code)

Max Activating Token Index: 483

Text #4

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0456. Min Act: -0.0003

Data Index: 435739 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1647506 (Python Code)

Max Activating Token Index: 981

Text #6

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1558154 (Python Code)

Max Activating Token Index: 240

Text #7

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1511967 (Python Code)

Max Activating Token Index: 801

Text #8

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1572445 (Python Code)

Max Activating Token Index: 368

Text #9

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0434. Min Act: -0.0003

Data Index: 1558747 (Python Code)

Max Activating Token Index: 116

Text #10

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1579107 (Python Code)

Max Activating Token Index: 679

Text #11

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0432. Min Act: -0.0003

Data Index: 1644632 (Python Code)

Max Activating Token Index: 575

Text #12

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0426. Min Act: -0.0003

Data Index: 482600 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0426. Min Act: -0.0003

Data Index: 1573088 (Python Code)

Max Activating Token Index: 231

Text #14

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1363714 (Python Code)

Max Activating Token Index: 123

Text #15

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0415. Min Act: -0.0003

Data Index: 1562468 (Python Code)

Max Activating Token Index: 237

Text #16

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1616150 (Python Code)

Max Activating Token Index: 206

Text #17

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0399. Min Act: -0.0003

Data Index: 1484685 (Python Code)

Max Activating Token Index: 762

Text #18

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0420. Min Act: -0.0003

Data Index: 583536 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0406. Min Act: -0.0003

Data Index: 1448923 (Python Code)

Max Activating Token Index: 776