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

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

Neuron 68 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: 0.0535. Min Range: -0.0535

Max Act: 0.0535. Min Act: -0.0003

Data Index: 1032060 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0426. Min Act: -0.0003

Data Index: 1067498 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0412. Min Act: -0.0003

Data Index: 1648698 (Python Code)

Max Activating Token Index: 67

Text #3

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0411. Min Act: -0.0002

Data Index: 692381 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1224414 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0388. Min Act: -0.0003

Data Index: 606537 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0399. Min Act: -0.0003

Data Index: 1379540 (Python Code)

Max Activating Token Index: 265

Text #7

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0368. Min Act: -0.0003

Data Index: 1140621 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0362. Min Act: -0.0003

Data Index: 1396230 (Python Code)

Max Activating Token Index: 838

Text #9

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0361. Min Act: -0.0003

Data Index: 255243 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0365. Min Act: -0.0003

Data Index: 1646879 (Python Code)

Max Activating Token Index: 737

Text #11

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0360. Min Act: -0.0003

Data Index: 1353198 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0365. Min Act: -0.0003

Data Index: 366973 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0353. Min Act: -0.0003

Data Index: 1192328 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0361. Min Act: -0.0003

Data Index: 1254176 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0360. Min Act: -0.0003

Data Index: 133419 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0353. Min Act: -0.0003

Data Index: 339337 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0352. Min Act: -0.0003

Data Index: 1461076 (Python Code)

Max Activating Token Index: 614

Text #18

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0348. Min Act: -0.0003

Data Index: 1053289 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0348. Min Act: -0.0002

Data Index: 173807 (C4 (Web Text))

Max Activating Token Index: 179