Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 547 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1620. Min Act: -0.0002

Data Index: 519824 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1600. Min Act: -0.0002

Data Index: 118054 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1500. Min Act: -0.0002

Data Index: 76448 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1423. Min Act: -0.0002

Data Index: 1326499 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1464. Min Act: -0.0002

Data Index: 1032101 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1477. Min Act: -0.0002

Data Index: 13649 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1450. Min Act: -0.0002

Data Index: 835472 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1438. Min Act: -0.0002

Data Index: 404128 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1363. Min Act: -0.0002

Data Index: 1063362 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1398. Min Act: -0.0002

Data Index: 1186103 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1315. Min Act: -0.0002

Data Index: 527961 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1313. Min Act: -0.0002

Data Index: 757715 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1317. Min Act: -0.0002

Data Index: 112208 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1311. Min Act: -0.0002

Data Index: 322304 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1357. Min Act: -0.0001

Data Index: 334776 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1328. Min Act: -0.0002

Data Index: 475643 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1251. Min Act: -0.0002

Data Index: 699201 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1291. Min Act: -0.0002

Data Index: 546087 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1270. Min Act: -0.0002

Data Index: 280260 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1168. Min Act: -0.0002

Data Index: 1107932 (C4 (Web Text))

Max Activating Token Index: 347