Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 770 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3311. Min Act: -0.0001

Data Index: 1482625 (Python Code)

Max Activating Token Index: 185

Text #1

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3341. Min Act: -0.0001

Data Index: 1655683 (Python Code)

Max Activating Token Index: 995

Text #2

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3010. Min Act: -0.0001

Data Index: 1588926 (Python Code)

Max Activating Token Index: 740

Text #3

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2917. Min Act: -0.0001

Data Index: 1433814 (Python Code)

Max Activating Token Index: 838

Text #4

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2925. Min Act: -0.0001

Data Index: 1484158 (Python Code)

Max Activating Token Index: 287

Text #5

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2895. Min Act: -0.0001

Data Index: 1363113 (Python Code)

Max Activating Token Index: 874

Text #6

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2620. Min Act: -0.0001

Data Index: 1439701 (Python Code)

Max Activating Token Index: 210

Text #7

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2833. Min Act: -0.0001

Data Index: 1459364 (Python Code)

Max Activating Token Index: 293

Text #8

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2615. Min Act: -0.0000

Data Index: 1528943 (Python Code)

Max Activating Token Index: 485

Text #9

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2607. Min Act: -0.0001

Data Index: 1470600 (Python Code)

Max Activating Token Index: 451

Text #10

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2452. Min Act: -0.0001

Data Index: 1411278 (Python Code)

Max Activating Token Index: 472

Text #11

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2412. Min Act: -0.0001

Data Index: 1643205 (Python Code)

Max Activating Token Index: 1010

Text #12

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2436. Min Act: -0.0001

Data Index: 1516534 (Python Code)

Max Activating Token Index: 764

Text #13

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2360. Min Act: -0.0001

Data Index: 1420903 (Python Code)

Max Activating Token Index: 90

Text #14

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2396. Min Act: -0.0001

Data Index: 1469653 (Python Code)

Max Activating Token Index: 389

Text #15

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2389. Min Act: -0.0001

Data Index: 1566087 (Python Code)

Max Activating Token Index: 48

Text #16

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2301. Min Act: -0.0001

Data Index: 1459040 (Python Code)

Max Activating Token Index: 38

Text #17

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2464. Min Act: -0.0001

Data Index: 1599823 (Python Code)

Max Activating Token Index: 219

Text #18

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2368. Min Act: -0.0001

Data Index: 1564893 (Python Code)

Max Activating Token Index: 1001

Text #19

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2427. Min Act: -0.0001

Data Index: 1613210 (Python Code)

Max Activating Token Index: 61