Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4487 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.6417. Min Range: -3.6417

Max Act: 3.6417. Min Act: -0.0000

Data Index: 199823 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 3.6417. Min Range: -3.6417

Max Act: 2.8160. Min Act: -0.0000

Data Index: 783720 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 3.6417. Min Range: -3.6417

Max Act: 2.6338. Min Act: -0.0000

Data Index: 69455 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 3.6417. Min Range: -3.6417

Max Act: 2.4385. Min Act: -0.0001

Data Index: 176718 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 3.6417. Min Range: -3.6417

Max Act: 2.3350. Min Act: -0.0001

Data Index: 1133395 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 3.6417. Min Range: -3.6417

Max Act: 2.5350. Min Act: -0.0001

Data Index: 166713 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 3.6417. Min Range: -3.6417

Max Act: 2.4219. Min Act: -0.0001

Data Index: 24222 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 3.6417. Min Range: -3.6417

Max Act: 2.5125. Min Act: -0.0000

Data Index: 308233 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 3.6417. Min Range: -3.6417

Max Act: 2.3269. Min Act: -0.0001

Data Index: 929002 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 3.6417. Min Range: -3.6417

Max Act: 2.4563. Min Act: -0.0001

Data Index: 288580 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 3.6417. Min Range: -3.6417

Max Act: 2.5622. Min Act: -0.0001

Data Index: 270460 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 3.6417. Min Range: -3.6417

Max Act: 2.4433. Min Act: -0.0001

Data Index: 206415 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 3.6417. Min Range: -3.6417

Max Act: 2.4477. Min Act: -0.0001

Data Index: 1049079 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 3.6417. Min Range: -3.6417

Max Act: 2.4336. Min Act: -0.0001

Data Index: 610580 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 3.6417. Min Range: -3.6417

Max Act: 2.4082. Min Act: -0.0001

Data Index: 223864 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 3.6417. Min Range: -3.6417

Max Act: 2.4382. Min Act: -0.0001

Data Index: 343350 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 3.6417. Min Range: -3.6417

Max Act: 2.5709. Min Act: -0.0000

Data Index: 1455724 (Python Code)

Max Activating Token Index: 1012

Text #17

Max Range: 3.6417. Min Range: -3.6417

Max Act: 2.3029. Min Act: -0.0001

Data Index: 62296 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 3.6417. Min Range: -3.6417

Max Act: 2.6215. Min Act: -0.0000

Data Index: 750925 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 3.6417. Min Range: -3.6417

Max Act: 2.4838. Min Act: -0.0000

Data Index: 535750 (C4 (Web Text))

Max Activating Token Index: 9