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

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

Neuron 1234 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: 0.6482. Min Range: -0.6482

Max Act: 0.6482. Min Act: -0.0001

Data Index: 1624230 (Python Code)

Max Activating Token Index: 542

Text #1

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.6301. Min Act: -0.0001

Data Index: 1461841 (Python Code)

Max Activating Token Index: 450

Text #2

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5961. Min Act: -0.0001

Data Index: 1581307 (Python Code)

Max Activating Token Index: 782

Text #3

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5993. Min Act: -0.0001

Data Index: 1409249 (Python Code)

Max Activating Token Index: 512

Text #4

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5824. Min Act: -0.0001

Data Index: 1655674 (Python Code)

Max Activating Token Index: 636

Text #5

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5477. Min Act: -0.0001

Data Index: 1407563 (Python Code)

Max Activating Token Index: 374

Text #6

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.6184. Min Act: -0.0001

Data Index: 1581468 (Python Code)

Max Activating Token Index: 936

Text #7

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5497. Min Act: -0.0001

Data Index: 1531031 (Python Code)

Max Activating Token Index: 985

Text #8

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5246. Min Act: -0.0001

Data Index: 1376092 (Python Code)

Max Activating Token Index: 95

Text #9

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5529. Min Act: -0.0001

Data Index: 1454482 (Python Code)

Max Activating Token Index: 248

Text #10

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5569. Min Act: -0.0001

Data Index: 1432946 (Python Code)

Max Activating Token Index: 455

Text #11

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5096. Min Act: -0.0001

Data Index: 1361377 (Python Code)

Max Activating Token Index: 613

Text #12

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5023. Min Act: -0.0001

Data Index: 1499177 (Python Code)

Max Activating Token Index: 626

Text #13

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5146. Min Act: -0.0001

Data Index: 1478321 (Python Code)

Max Activating Token Index: 21

Text #14

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.4665. Min Act: -0.0001

Data Index: 1624430 (Python Code)

Max Activating Token Index: 708

Text #15

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.4993. Min Act: -0.0001

Data Index: 1438721 (Python Code)

Max Activating Token Index: 135

Text #16

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.4967. Min Act: -0.0001

Data Index: 1623317 (Python Code)

Max Activating Token Index: 573

Text #17

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.4956. Min Act: -0.0001

Data Index: 1655215 (Python Code)

Max Activating Token Index: 81

Text #18

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.4657. Min Act: -0.0001

Data Index: 1553833 (Python Code)

Max Activating Token Index: 67

Text #19

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.4632. Min Act: -0.0001

Data Index: 1617165 (Python Code)

Max Activating Token Index: 45