Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1050 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0597. Min Act: -0.0003

Data Index: 285316 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0558. Min Act: -0.0003

Data Index: 972225 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0533. Min Act: -0.0003

Data Index: 1347365 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0500. Min Act: -0.0003

Data Index: 297482 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0460. Min Act: -0.0003

Data Index: 1259053 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0455. Min Act: -0.0003

Data Index: 110789 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0444. Min Act: -0.0003

Data Index: 358742 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0435. Min Act: -0.0003

Data Index: 606525 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1172622 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0426. Min Act: -0.0003

Data Index: 33046 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0429. Min Act: -0.0003

Data Index: 929651 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0436. Min Act: -0.0003

Data Index: 472966 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0442. Min Act: -0.0003

Data Index: 83930 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0408. Min Act: -0.0003

Data Index: 452709 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0423. Min Act: -0.0003

Data Index: 779269 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0438. Min Act: -0.0003

Data Index: 796671 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0444. Min Act: -0.0003

Data Index: 921373 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0429. Min Act: -0.0003

Data Index: 500860 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0422. Min Act: -0.0003

Data Index: 773868 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0424. Min Act: -0.0003

Data Index: 1224432 (C4 (Web Text))

Max Activating Token Index: 322