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

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

Neuron 1940 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.7981. Min Act: -0.0001

Data Index: 1368369 (Python Code)

Max Activating Token Index: 841

Text #1

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.7122. Min Act: -0.0001

Data Index: 1579956 (Python Code)

Max Activating Token Index: 691

Text #2

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6129. Min Act: -0.0001

Data Index: 1423145 (Python Code)

Max Activating Token Index: 813

Text #3

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5879. Min Act: -0.0001

Data Index: 1398832 (Python Code)

Max Activating Token Index: 94

Text #4

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6020. Min Act: -0.0001

Data Index: 1573783 (Python Code)

Max Activating Token Index: 19

Text #5

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6146. Min Act: -0.0001

Data Index: 1436408 (Python Code)

Max Activating Token Index: 139

Text #6

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5619. Min Act: -0.0001

Data Index: 1533548 (Python Code)

Max Activating Token Index: 974

Text #7

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5859. Min Act: -0.0001

Data Index: 1565169 (Python Code)

Max Activating Token Index: 711

Text #8

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5761. Min Act: -0.0001

Data Index: 1566124 (Python Code)

Max Activating Token Index: 215

Text #9

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5380. Min Act: -0.0001

Data Index: 1436198 (Python Code)

Max Activating Token Index: 136

Text #10

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5503. Min Act: -0.0001

Data Index: 1455771 (Python Code)

Max Activating Token Index: 888

Text #11

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5787. Min Act: -0.0001

Data Index: 1630933 (Python Code)

Max Activating Token Index: 943

Text #12

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5454. Min Act: -0.0001

Data Index: 1530911 (Python Code)

Max Activating Token Index: 128

Text #13

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5386. Min Act: -0.0001

Data Index: 1511966 (Python Code)

Max Activating Token Index: 414

Text #14

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.4862. Min Act: -0.0001

Data Index: 1519396 (Python Code)

Max Activating Token Index: 695

Text #15

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5031. Min Act: -0.0001

Data Index: 1544141 (Python Code)

Max Activating Token Index: 563

Text #16

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5331. Min Act: -0.0001

Data Index: 1493836 (Python Code)

Max Activating Token Index: 418

Text #17

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5305. Min Act: -0.0001

Data Index: 1429187 (Python Code)

Max Activating Token Index: 83

Text #18

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5328. Min Act: -0.0001

Data Index: 1544484 (Python Code)

Max Activating Token Index: 692

Text #19

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5402. Min Act: -0.0001

Data Index: 1370906 (Python Code)

Max Activating Token Index: 552