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

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

Neuron 91 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.4532. Min Act: -0.0001

Data Index: 1491123 (Python Code)

Max Activating Token Index: 706

Text #1

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3878. Min Act: -0.0001

Data Index: 1549543 (Python Code)

Max Activating Token Index: 961

Text #2

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3731. Min Act: -0.0001

Data Index: 1361496 (Python Code)

Max Activating Token Index: 50

Text #3

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3734. Min Act: -0.0001

Data Index: 1466078 (Python Code)

Max Activating Token Index: 811

Text #4

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3721. Min Act: -0.0001

Data Index: 1634255 (Python Code)

Max Activating Token Index: 290

Text #5

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3388. Min Act: -0.0001

Data Index: 1488893 (Python Code)

Max Activating Token Index: 346

Text #6

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3373. Min Act: -0.0001

Data Index: 1575271 (Python Code)

Max Activating Token Index: 890

Text #7

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3482. Min Act: -0.0001

Data Index: 1459554 (Python Code)

Max Activating Token Index: 127

Text #8

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3450. Min Act: -0.0001

Data Index: 1408521 (Python Code)

Max Activating Token Index: 131

Text #9

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3422. Min Act: -0.0001

Data Index: 1531677 (Python Code)

Max Activating Token Index: 451

Text #10

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3285. Min Act: -0.0001

Data Index: 1595661 (Python Code)

Max Activating Token Index: 51

Text #11

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3247. Min Act: -0.0001

Data Index: 1381960 (Python Code)

Max Activating Token Index: 678

Text #12

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3310. Min Act: -0.0001

Data Index: 1559103 (Python Code)

Max Activating Token Index: 43

Text #13

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3202. Min Act: -0.0001

Data Index: 1633049 (Python Code)

Max Activating Token Index: 947

Text #14

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3296. Min Act: -0.0001

Data Index: 1633338 (Python Code)

Max Activating Token Index: 253

Text #15

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3184. Min Act: -0.0001

Data Index: 1608003 (Python Code)

Max Activating Token Index: 227

Text #16

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3281. Min Act: -0.0001

Data Index: 1526245 (Python Code)

Max Activating Token Index: 536

Text #17

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3298. Min Act: -0.0001

Data Index: 1431060 (Python Code)

Max Activating Token Index: 173

Text #18

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3274. Min Act: -0.0001

Data Index: 1624167 (Python Code)

Max Activating Token Index: 209

Text #19

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3269. Min Act: -0.0001

Data Index: 1517276 (Python Code)

Max Activating Token Index: 84