Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2613 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.7421. Min Act: -0.0000

Data Index: 1529831 (Python Code)

Max Activating Token Index: 631

Text #1

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.7547. Min Act: -0.0000

Data Index: 1426757 (Python Code)

Max Activating Token Index: 957

Text #2

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1516692 (Python Code)

Max Activating Token Index: 606

Text #3

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6988. Min Act: -0.0000

Data Index: 1579198 (Python Code)

Max Activating Token Index: 728

Text #4

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.7063. Min Act: -0.0000

Data Index: 1371246 (Python Code)

Max Activating Token Index: 688

Text #5

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6761. Min Act: -0.0000

Data Index: 1633386 (Python Code)

Max Activating Token Index: 728

Text #6

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6981. Min Act: -0.0000

Data Index: 1498884 (Python Code)

Max Activating Token Index: 439

Text #7

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1588427 (Python Code)

Max Activating Token Index: 967

Text #8

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6495. Min Act: -0.0000

Data Index: 1592735 (Python Code)

Max Activating Token Index: 627

Text #9

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1421982 (Python Code)

Max Activating Token Index: 406

Text #10

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6670. Min Act: -0.0000

Data Index: 1512385 (Python Code)

Max Activating Token Index: 89

Text #11

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1471928 (Python Code)

Max Activating Token Index: 636

Text #12

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6226. Min Act: -0.0000

Data Index: 1467180 (Python Code)

Max Activating Token Index: 942

Text #13

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6198. Min Act: -0.0000

Data Index: 1656108 (Python Code)

Max Activating Token Index: 547

Text #14

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6174. Min Act: -0.0000

Data Index: 1502772 (Python Code)

Max Activating Token Index: 641

Text #15

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1418979 (Python Code)

Max Activating Token Index: 920

Text #16

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6352. Min Act: -0.0000

Data Index: 1534114 (Python Code)

Max Activating Token Index: 465

Text #17

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6283. Min Act: -0.0000

Data Index: 1546441 (Python Code)

Max Activating Token Index: 436

Text #18

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6316. Min Act: -0.0000

Data Index: 1362359 (Python Code)

Max Activating Token Index: 826

Text #19

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6317. Min Act: -0.0000

Data Index: 132466 (C4 (Web Text))

Max Activating Token Index: 968