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

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

Neuron 1325 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1757. Min Range: -1.1757

Max Act: 1.1757. Min Act: -0.0001

Data Index: 755394 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 1.1757. Min Range: -1.1757

Max Act: 1.0966. Min Act: -0.0001

Data Index: 1488200 (Python Code)

Max Activating Token Index: 705

Text #2

Max Range: 1.1757. Min Range: -1.1757

Max Act: 1.0725. Min Act: -0.0001

Data Index: 926502 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.9694. Min Act: -0.0001

Data Index: 1428338 (Python Code)

Max Activating Token Index: 364

Text #4

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.9180. Min Act: -0.0001

Data Index: 1207674 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.9447. Min Act: -0.0000

Data Index: 1050104 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 1.1757. Min Range: -1.1757

Max Act: 1.0092. Min Act: -0.0000

Data Index: 1390483 (Python Code)

Max Activating Token Index: 970

Text #7

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.9639. Min Act: -0.0001

Data Index: 1362025 (Python Code)

Max Activating Token Index: 985

Text #8

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.9174. Min Act: -0.0001

Data Index: 874655 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.9806. Min Act: -0.0001

Data Index: 1609157 (Python Code)

Max Activating Token Index: 996

Text #10

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8981. Min Act: -0.0000

Data Index: 581858 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8217. Min Act: -0.0000

Data Index: 1217546 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.9231. Min Act: -0.0001

Data Index: 1227401 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8789. Min Act: -0.0001

Data Index: 1631948 (Python Code)

Max Activating Token Index: 22

Text #14

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8783. Min Act: -0.0000

Data Index: 1599110 (Python Code)

Max Activating Token Index: 164

Text #15

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8526. Min Act: -0.0001

Data Index: 617266 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.9034. Min Act: -0.0000

Data Index: 281987 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.9040. Min Act: -0.0000

Data Index: 621545 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.9300. Min Act: -0.0000

Data Index: 1222828 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8679. Min Act: -0.0001

Data Index: 1441248 (Python Code)

Max Activating Token Index: 944