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

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

Neuron 2581 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1443597 (Python Code)

Max Activating Token Index: 494

Text #1

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1128. Min Act: -0.0001

Data Index: 1522772 (Python Code)

Max Activating Token Index: 457

Text #2

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0914. Min Act: -0.0001

Data Index: 1066685 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1174. Min Act: -0.0001

Data Index: 1536569 (Python Code)

Max Activating Token Index: 556

Text #4

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1390930 (Python Code)

Max Activating Token Index: 895

Text #5

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1062. Min Act: -0.0001

Data Index: 1399345 (Python Code)

Max Activating Token Index: 643

Text #6

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1095. Min Act: -0.0001

Data Index: 1538931 (Python Code)

Max Activating Token Index: 408

Text #7

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1074. Min Act: -0.0001

Data Index: 1461795 (Python Code)

Max Activating Token Index: 375

Text #8

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1131. Min Act: -0.0001

Data Index: 1476113 (Python Code)

Max Activating Token Index: 511

Text #9

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1212. Min Act: -0.0001

Data Index: 1446849 (Python Code)

Max Activating Token Index: 719

Text #10

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1060. Min Act: -0.0001

Data Index: 1429627 (Python Code)

Max Activating Token Index: 408

Text #11

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1053. Min Act: -0.0001

Data Index: 1535181 (Python Code)

Max Activating Token Index: 489

Text #12

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1078. Min Act: -0.0001

Data Index: 1556053 (Python Code)

Max Activating Token Index: 356

Text #13

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0948. Min Act: -0.0001

Data Index: 1368407 (Python Code)

Max Activating Token Index: 535

Text #14

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0933. Min Act: -0.0001

Data Index: 685612 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0904. Min Act: -0.0001

Data Index: 892873 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0793. Min Act: -0.0001

Data Index: 1109433 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0880. Min Act: -0.0001

Data Index: 1642652 (Python Code)

Max Activating Token Index: 56

Text #18

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0920. Min Act: -0.0001

Data Index: 847718 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0846. Min Act: -0.0001

Data Index: 386858 (C4 (Web Text))

Max Activating Token Index: 618