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

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

Neuron 990 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1110. Min Act: -0.0001

Data Index: 971665 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1113. Min Act: -0.0001

Data Index: 462161 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1044. Min Act: -0.0002

Data Index: 925519 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1556534 (Python Code)

Max Activating Token Index: 68

Text #4

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1037. Min Act: -0.0001

Data Index: 52773 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0934. Min Act: -0.0001

Data Index: 60988 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0825. Min Act: -0.0001

Data Index: 1471543 (Python Code)

Max Activating Token Index: 363

Text #7

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0983. Min Act: -0.0001

Data Index: 246455 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1561336 (Python Code)

Max Activating Token Index: 618

Text #9

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1028. Min Act: -0.0001

Data Index: 1570862 (Python Code)

Max Activating Token Index: 999

Text #10

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0964. Min Act: -0.0001

Data Index: 1583597 (Python Code)

Max Activating Token Index: 460

Text #11

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0985. Min Act: -0.0001

Data Index: 349502 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1016. Min Act: -0.0001

Data Index: 923683 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1004. Min Act: -0.0001

Data Index: 976515 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0998. Min Act: -0.0001

Data Index: 1364824 (Python Code)

Max Activating Token Index: 969

Text #15

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0930. Min Act: -0.0001

Data Index: 991947 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0931. Min Act: -0.0001

Data Index: 1486567 (Python Code)

Max Activating Token Index: 388

Text #17

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0932. Min Act: -0.0001

Data Index: 1610433 (Python Code)

Max Activating Token Index: 991

Text #18

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0796. Min Act: -0.0001

Data Index: 1466819 (Python Code)

Max Activating Token Index: 263

Text #19

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0857. Min Act: -0.0001

Data Index: 1443380 (Python Code)

Max Activating Token Index: 31