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

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

Neuron 341 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.9324. Min Act: -0.0001

Data Index: 1316047 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 1.0365. Min Range: -1.0365

Max Act: 1.0306. Min Act: -0.0001

Data Index: 25056 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.9674. Min Act: -0.0001

Data Index: 1543949 (Python Code)

Max Activating Token Index: 382

Text #3

Max Range: 1.0365. Min Range: -1.0365

Max Act: 1.0365. Min Act: -0.0001

Data Index: 921778 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.9598. Min Act: -0.0001

Data Index: 211721 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.9902. Min Act: -0.0001

Data Index: 1568725 (Python Code)

Max Activating Token Index: 685

Text #6

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.9732. Min Act: -0.0001

Data Index: 523700 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.9144. Min Act: -0.0001

Data Index: 1565049 (Python Code)

Max Activating Token Index: 398

Text #8

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.9124. Min Act: -0.0001

Data Index: 92832 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.9272. Min Act: -0.0001

Data Index: 325105 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.9018. Min Act: -0.0001

Data Index: 1590574 (Python Code)

Max Activating Token Index: 71

Text #11

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.8756. Min Act: -0.0001

Data Index: 950343 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.8519. Min Act: -0.0001

Data Index: 1476352 (Python Code)

Max Activating Token Index: 334

Text #13

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.9487. Min Act: -0.0001

Data Index: 608665 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.8939. Min Act: -0.0001

Data Index: 1099042 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.8905. Min Act: -0.0001

Data Index: 254843 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.8895. Min Act: -0.0001

Data Index: 387186 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.9724. Min Act: -0.0001

Data Index: 1253536 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.8428. Min Act: -0.0001

Data Index: 304112 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.8729. Min Act: -0.0001

Data Index: 37474 (C4 (Web Text))

Max Activating Token Index: 230