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

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

Neuron 585 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: 0.1614. Min Range: -0.1614

Max Act: 0.1614. Min Act: -0.0003

Data Index: 633536 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1432. Min Act: -0.0003

Data Index: 1101594 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1418. Min Act: -0.0003

Data Index: 57481 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1360. Min Act: -0.0003

Data Index: 584122 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1333. Min Act: -0.0003

Data Index: 784688 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1378. Min Act: -0.0003

Data Index: 1049898 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1403. Min Act: -0.0003

Data Index: 705818 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1349. Min Act: -0.0003

Data Index: 568649 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1403. Min Act: -0.0003

Data Index: 985107 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1346. Min Act: -0.0003

Data Index: 405824 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1336. Min Act: -0.0003

Data Index: 346641 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1330. Min Act: -0.0003

Data Index: 788113 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1317. Min Act: -0.0003

Data Index: 635003 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1265. Min Act: -0.0003

Data Index: 1266375 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1260. Min Act: -0.0003

Data Index: 1325119 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1303. Min Act: -0.0003

Data Index: 409811 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1302. Min Act: -0.0003

Data Index: 1235804 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1338. Min Act: -0.0003

Data Index: 1109673 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1236. Min Act: -0.0003

Data Index: 556791 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1334. Min Act: -0.0003

Data Index: 1003133 (C4 (Web Text))

Max Activating Token Index: 900