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

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

Neuron 525 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: 0.0377. Min Range: -0.0377

Max Act: 0.0377. Min Act: -0.0001

Data Index: 1498201 (Python Code)

Max Activating Token Index: 772

Text #1

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0359. Min Act: -0.0001

Data Index: 1517397 (Python Code)

Max Activating Token Index: 250

Text #2

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0342. Min Act: -0.0001

Data Index: 1595218 (Python Code)

Max Activating Token Index: 142

Text #3

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0319. Min Act: -0.0001

Data Index: 1531209 (Python Code)

Max Activating Token Index: 64

Text #4

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0278. Min Act: -0.0001

Data Index: 1483117 (Python Code)

Max Activating Token Index: 306

Text #5

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0281. Min Act: -0.0001

Data Index: 1573946 (Python Code)

Max Activating Token Index: 30

Text #6

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0282. Min Act: -0.0001

Data Index: 1638356 (Python Code)

Max Activating Token Index: 91

Text #7

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0283. Min Act: -0.0001

Data Index: 507120 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0269. Min Act: -0.0001

Data Index: 1472360 (Python Code)

Max Activating Token Index: 57

Text #9

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0275. Min Act: -0.0001

Data Index: 1534218 (Python Code)

Max Activating Token Index: 72

Text #10

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0247. Min Act: -0.0001

Data Index: 89364 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0255. Min Act: -0.0001

Data Index: 1480387 (Python Code)

Max Activating Token Index: 128

Text #12

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0257. Min Act: -0.0001

Data Index: 1604050 (Python Code)

Max Activating Token Index: 60

Text #13

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0253. Min Act: -0.0001

Data Index: 1440772 (Python Code)

Max Activating Token Index: 98

Text #14

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0258. Min Act: -0.0001

Data Index: 1508637 (Python Code)

Max Activating Token Index: 379

Text #15

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0244. Min Act: -0.0001

Data Index: 1435015 (Python Code)

Max Activating Token Index: 39

Text #16

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0251. Min Act: -0.0001

Data Index: 1576993 (Python Code)

Max Activating Token Index: 35

Text #17

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0238. Min Act: -0.0001

Data Index: 1541362 (Python Code)

Max Activating Token Index: 102

Text #18

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0247. Min Act: -0.0001

Data Index: 1499520 (Python Code)

Max Activating Token Index: 947

Text #19

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0227. Min Act: -0.0001

Data Index: 1397379 (Python Code)

Max Activating Token Index: 741