Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2389 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1796. Min Act: -0.0004

Data Index: 1298857 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1522. Min Act: -0.0004

Data Index: 541363 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1511. Min Act: -0.0004

Data Index: 951246 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1472. Min Act: -0.0004

Data Index: 318997 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1410. Min Act: -0.0004

Data Index: 1035593 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1512. Min Act: -0.0004

Data Index: 1081542 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1517. Min Act: -0.0004

Data Index: 826558 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1450. Min Act: -0.0004

Data Index: 49288 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1311. Min Act: -0.0004

Data Index: 824707 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1431. Min Act: -0.0004

Data Index: 502969 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1372. Min Act: -0.0004

Data Index: 687932 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1331. Min Act: -0.0004

Data Index: 43595 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1276. Min Act: -0.0004

Data Index: 448658 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1344. Min Act: -0.0004

Data Index: 1029055 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1336. Min Act: -0.0004

Data Index: 431679 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1296. Min Act: -0.0004

Data Index: 199476 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1280. Min Act: -0.0004

Data Index: 800440 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1318. Min Act: -0.0004

Data Index: 503783 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1367. Min Act: -0.0004

Data Index: 968807 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1248. Min Act: -0.0004

Data Index: 1200487 (C4 (Web Text))

Max Activating Token Index: 821