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

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

Neuron 3671 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2070. Min Range: -1.2070

Max Act: 1.2070. Min Act: -0.0001

Data Index: 495696 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 1.2070. Min Range: -1.2070

Max Act: 1.0565. Min Act: -0.0001

Data Index: 1214373 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 1.2070. Min Range: -1.2070

Max Act: 1.0742. Min Act: -0.0000

Data Index: 1417479 (Python Code)

Max Activating Token Index: 35

Text #3

Max Range: 1.2070. Min Range: -1.2070

Max Act: 1.0872. Min Act: -0.0001

Data Index: 1488626 (Python Code)

Max Activating Token Index: 236

Text #4

Max Range: 1.2070. Min Range: -1.2070

Max Act: 1.0676. Min Act: -0.0001

Data Index: 1474593 (Python Code)

Max Activating Token Index: 886

Text #5

Max Range: 1.2070. Min Range: -1.2070

Max Act: 1.0807. Min Act: -0.0001

Data Index: 1588186 (Python Code)

Max Activating Token Index: 327

Text #6

Max Range: 1.2070. Min Range: -1.2070

Max Act: 1.0801. Min Act: -0.0000

Data Index: 1455212 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 1.2070. Min Range: -1.2070

Max Act: 1.0106. Min Act: -0.0001

Data Index: 1508341 (Python Code)

Max Activating Token Index: 980

Text #8

Max Range: 1.2070. Min Range: -1.2070

Max Act: 1.0213. Min Act: -0.0001

Data Index: 802176 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 1.2070. Min Range: -1.2070

Max Act: 1.0709. Min Act: -0.0001

Data Index: 1517183 (Python Code)

Max Activating Token Index: 1005

Text #10

Max Range: 1.2070. Min Range: -1.2070

Max Act: 1.0446. Min Act: -0.0001

Data Index: 1585077 (Python Code)

Max Activating Token Index: 990

Text #11

Max Range: 1.2070. Min Range: -1.2070

Max Act: 1.0763. Min Act: -0.0001

Data Index: 1376465 (Python Code)

Max Activating Token Index: 950

Text #12

Max Range: 1.2070. Min Range: -1.2070

Max Act: 1.0323. Min Act: -0.0001

Data Index: 1572597 (Python Code)

Max Activating Token Index: 821

Text #13

Max Range: 1.2070. Min Range: -1.2070

Max Act: 0.9763. Min Act: -0.0001

Data Index: 1442173 (Python Code)

Max Activating Token Index: 854

Text #14

Max Range: 1.2070. Min Range: -1.2070

Max Act: 1.0340. Min Act: -0.0001

Data Index: 1432275 (Python Code)

Max Activating Token Index: 982

Text #15

Max Range: 1.2070. Min Range: -1.2070

Max Act: 1.0595. Min Act: -0.0001

Data Index: 1542111 (Python Code)

Max Activating Token Index: 557

Text #16

Max Range: 1.2070. Min Range: -1.2070

Max Act: 1.0255. Min Act: -0.0001

Data Index: 1582376 (Python Code)

Max Activating Token Index: 1015

Text #17

Max Range: 1.2070. Min Range: -1.2070

Max Act: 1.0265. Min Act: -0.0001

Data Index: 1416813 (Python Code)

Max Activating Token Index: 924

Text #18

Max Range: 1.2070. Min Range: -1.2070

Max Act: 0.9988. Min Act: -0.0001

Data Index: 1406348 (Python Code)

Max Activating Token Index: 951

Text #19

Max Range: 1.2070. Min Range: -1.2070

Max Act: 0.9953. Min Act: -0.0001

Data Index: 1406621 (Python Code)

Max Activating Token Index: 941