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

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

Neuron 798 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.2258. Min Act: -0.0001

Data Index: 1489393 (Python Code)

Max Activating Token Index: 180

Text #1

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.2304. Min Act: -0.0000

Data Index: 1370283 (Python Code)

Max Activating Token Index: 953

Text #2

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.2212. Min Act: -0.0001

Data Index: 498536 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1956. Min Act: -0.0001

Data Index: 1574586 (Python Code)

Max Activating Token Index: 1008

Text #4

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1894. Min Act: -0.0001

Data Index: 1431699 (Python Code)

Max Activating Token Index: 962

Text #5

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1989. Min Act: -0.0001

Data Index: 1181256 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1855. Min Act: -0.0001

Data Index: 916231 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1613. Min Act: -0.0001

Data Index: 1587505 (Python Code)

Max Activating Token Index: 183

Text #8

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1598. Min Act: -0.0001

Data Index: 1607365 (Python Code)

Max Activating Token Index: 833

Text #9

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1706. Min Act: -0.0001

Data Index: 1645015 (Python Code)

Max Activating Token Index: 723

Text #10

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1844. Min Act: -0.0001

Data Index: 514404 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1569. Min Act: -0.0001

Data Index: 1412418 (Python Code)

Max Activating Token Index: 363

Text #12

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1622. Min Act: -0.0000

Data Index: 1636362 (Python Code)

Max Activating Token Index: 472

Text #13

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1842. Min Act: -0.0001

Data Index: 425829 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1723. Min Act: -0.0001

Data Index: 789340 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1534. Min Act: -0.0001

Data Index: 1577066 (Python Code)

Max Activating Token Index: 998

Text #16

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1733. Min Act: -0.0000

Data Index: 1599524 (Python Code)

Max Activating Token Index: 384

Text #17

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1596. Min Act: -0.0001

Data Index: 1434295 (Python Code)

Max Activating Token Index: 578

Text #18

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1690. Min Act: -0.0001

Data Index: 1155969 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1596. Min Act: -0.0000

Data Index: 1463510 (Python Code)

Max Activating Token Index: 467