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

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

Neuron 4740 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.9056. Min Act: -0.0000

Data Index: 1489001 (Python Code)

Max Activating Token Index: 407

Text #1

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.8334. Min Act: -0.0000

Data Index: 1459523 (Python Code)

Max Activating Token Index: 398

Text #2

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.8240. Min Act: -0.0000

Data Index: 1620673 (Python Code)

Max Activating Token Index: 975

Text #3

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.8460. Min Act: -0.0000

Data Index: 1619582 (Python Code)

Max Activating Token Index: 481

Text #4

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.7902. Min Act: -0.0000

Data Index: 1420311 (Python Code)

Max Activating Token Index: 604

Text #5

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.7631. Min Act: -0.0000

Data Index: 1471026 (Python Code)

Max Activating Token Index: 786

Text #6

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.7882. Min Act: -0.0000

Data Index: 1463745 (Python Code)

Max Activating Token Index: 338

Text #7

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1602507 (Python Code)

Max Activating Token Index: 511

Text #8

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.7934. Min Act: -0.0000

Data Index: 1542591 (Python Code)

Max Activating Token Index: 87

Text #9

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.7845. Min Act: -0.0000

Data Index: 1559112 (Python Code)

Max Activating Token Index: 657

Text #10

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.7598. Min Act: -0.0000

Data Index: 1566215 (Python Code)

Max Activating Token Index: 665

Text #11

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.7609. Min Act: -0.0000

Data Index: 1620529 (Python Code)

Max Activating Token Index: 970

Text #12

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1595365 (Python Code)

Max Activating Token Index: 878

Text #13

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.6287. Min Act: -0.0000

Data Index: 743312 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.6210. Min Act: -0.0000

Data Index: 1643736 (Python Code)

Max Activating Token Index: 21

Text #15

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.6029. Min Act: -0.0000

Data Index: 1057994 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1558705 (Python Code)

Max Activating Token Index: 618

Text #17

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.6152. Min Act: -0.0000

Data Index: 1420684 (Python Code)

Max Activating Token Index: 725

Text #18

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.5260. Min Act: -0.0000

Data Index: 1631652 (Python Code)

Max Activating Token Index: 465

Text #19

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.5350. Min Act: -0.0000

Data Index: 1336296 (C4 (Web Text))

Max Activating Token Index: 540