Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3179 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.7328. Min Range: -3.7328

Max Act: 3.7328. Min Act: -0.0000

Data Index: 1499706 (Python Code)

Max Activating Token Index: 143

Text #1

Max Range: 3.7328. Min Range: -3.7328

Max Act: 3.5355. Min Act: -0.0000

Data Index: 1567140 (Python Code)

Max Activating Token Index: 942

Text #2

Max Range: 3.7328. Min Range: -3.7328

Max Act: 2.7832. Min Act: -0.0000

Data Index: 1509832 (Python Code)

Max Activating Token Index: 107

Text #3

Max Range: 3.7328. Min Range: -3.7328

Max Act: 2.5475. Min Act: -0.0000

Data Index: 669230 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 3.7328. Min Range: -3.7328

Max Act: 2.4977. Min Act: -0.0000

Data Index: 1536377 (Python Code)

Max Activating Token Index: 414

Text #5

Max Range: 3.7328. Min Range: -3.7328

Max Act: 2.4234. Min Act: -0.0000

Data Index: 1523889 (Python Code)

Max Activating Token Index: 625

Text #6

Max Range: 3.7328. Min Range: -3.7328

Max Act: 2.3748. Min Act: -0.0000

Data Index: 169963 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 3.7328. Min Range: -3.7328

Max Act: 2.3593. Min Act: -0.0000

Data Index: 1530936 (Python Code)

Max Activating Token Index: 857

Text #8

Max Range: 3.7328. Min Range: -3.7328

Max Act: 2.4594. Min Act: -0.0000

Data Index: 861553 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 3.7328. Min Range: -3.7328

Max Act: 2.3230. Min Act: -0.0000

Data Index: 1409017 (Python Code)

Max Activating Token Index: 495

Text #10

Max Range: 3.7328. Min Range: -3.7328

Max Act: 2.5546. Min Act: -0.0000

Data Index: 1394400 (Python Code)

Max Activating Token Index: 729

Text #11

Max Range: 3.7328. Min Range: -3.7328

Max Act: 2.1895. Min Act: -0.0000

Data Index: 956041 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 3.7328. Min Range: -3.7328

Max Act: 2.1486. Min Act: -0.0000

Data Index: 1570114 (Python Code)

Max Activating Token Index: 643

Text #13

Max Range: 3.7328. Min Range: -3.7328

Max Act: 2.2349. Min Act: -0.0000

Data Index: 1388200 (Python Code)

Max Activating Token Index: 995

Text #14

Max Range: 3.7328. Min Range: -3.7328

Max Act: 2.1086. Min Act: -0.0000

Data Index: 226833 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 3.7328. Min Range: -3.7328

Max Act: 2.2241. Min Act: -0.0000

Data Index: 1598062 (Python Code)

Max Activating Token Index: 300

Text #16

Max Range: 3.7328. Min Range: -3.7328

Max Act: 2.3474. Min Act: -0.0000

Data Index: 431852 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 3.7328. Min Range: -3.7328

Max Act: 2.2217. Min Act: -0.0000

Data Index: 1491546 (Python Code)

Max Activating Token Index: 638

Text #18

Max Range: 3.7328. Min Range: -3.7328

Max Act: 2.0009. Min Act: -0.0000

Data Index: 1355113 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 3.7328. Min Range: -3.7328

Max Act: 2.1013. Min Act: -0.0000

Data Index: 876734 (C4 (Web Text))

Max Activating Token Index: 903