Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 317 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1209259 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2192. Min Act: -0.0000

Data Index: 1655212 (Python Code)

Max Activating Token Index: 501

Text #2

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2113. Min Act: -0.0001

Data Index: 1335625 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2207. Min Act: -0.0000

Data Index: 240917 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2057. Min Act: -0.0001

Data Index: 1379904 (Python Code)

Max Activating Token Index: 407

Text #5

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2104. Min Act: -0.0001

Data Index: 1474959 (Python Code)

Max Activating Token Index: 52

Text #6

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2159. Min Act: -0.0001

Data Index: 1458170 (Python Code)

Max Activating Token Index: 231

Text #7

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2064. Min Act: -0.0000

Data Index: 646307 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2010. Min Act: -0.0000

Data Index: 580168 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1941. Min Act: -0.0001

Data Index: 1237722 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1962. Min Act: -0.0000

Data Index: 375256 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2018. Min Act: -0.0000

Data Index: 1443969 (Python Code)

Max Activating Token Index: 750

Text #12

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1282635 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2106. Min Act: -0.0001

Data Index: 18179 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2018. Min Act: -0.0000

Data Index: 1629611 (Python Code)

Max Activating Token Index: 95

Text #15

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1935. Min Act: -0.0001

Data Index: 137286 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1974. Min Act: -0.0001

Data Index: 881930 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1747. Min Act: -0.0000

Data Index: 1034835 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1964. Min Act: -0.0001

Data Index: 377982 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1953. Min Act: -0.0001

Data Index: 1487338 (Python Code)

Max Activating Token Index: 289