Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4488 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0492. Min Act: -0.0001

Data Index: 580712 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0363. Min Act: -0.0001

Data Index: 1215265 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0395. Min Act: -0.0001

Data Index: 434727 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0399. Min Act: -0.0001

Data Index: 1286008 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0350. Min Act: -0.0001

Data Index: 1424006 (Python Code)

Max Activating Token Index: 620

Text #5

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0357. Min Act: -0.0001

Data Index: 173900 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0361. Min Act: -0.0001

Data Index: 971210 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0324. Min Act: -0.0001

Data Index: 1025047 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0343. Min Act: -0.0001

Data Index: 771945 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0338. Min Act: -0.0001

Data Index: 457371 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0385. Min Act: -0.0001

Data Index: 1525312 (Python Code)

Max Activating Token Index: 146

Text #11

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0328. Min Act: -0.0002

Data Index: 470214 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0319. Min Act: -0.0001

Data Index: 1369864 (Python Code)

Max Activating Token Index: 259

Text #13

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0321. Min Act: -0.0001

Data Index: 1467843 (Python Code)

Max Activating Token Index: 802

Text #14

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0305. Min Act: -0.0001

Data Index: 634369 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0293. Min Act: -0.0001

Data Index: 745438 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0284. Min Act: -0.0001

Data Index: 1201351 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0242. Min Act: -0.0001

Data Index: 334630 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0300. Min Act: -0.0001

Data Index: 725237 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0282. Min Act: -0.0001

Data Index: 766747 (C4 (Web Text))

Max Activating Token Index: 353