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

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

Neuron 2888 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.7859. Min Act: -0.0000

Data Index: 1605321 (Python Code)

Max Activating Token Index: 950

Text #1

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.8424. Min Act: -0.0000

Data Index: 1628276 (Python Code)

Max Activating Token Index: 988

Text #2

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.8118. Min Act: -0.0001

Data Index: 1631653 (Python Code)

Max Activating Token Index: 919

Text #3

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.8009. Min Act: -0.0001

Data Index: 1463693 (Python Code)

Max Activating Token Index: 797

Text #4

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.7412. Min Act: -0.0000

Data Index: 1431525 (Python Code)

Max Activating Token Index: 899

Text #5

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.7772. Min Act: -0.0001

Data Index: 1432484 (Python Code)

Max Activating Token Index: 600

Text #6

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.7209. Min Act: -0.0000

Data Index: 1469899 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.7276. Min Act: -0.0000

Data Index: 1413162 (Python Code)

Max Activating Token Index: 847

Text #8

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.6846. Min Act: -0.0001

Data Index: 1646918 (Python Code)

Max Activating Token Index: 906

Text #9

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.7328. Min Act: -0.0000

Data Index: 1446327 (Python Code)

Max Activating Token Index: 273

Text #10

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.7058. Min Act: -0.0001

Data Index: 1415920 (Python Code)

Max Activating Token Index: 942

Text #11

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.7123. Min Act: -0.0000

Data Index: 1413222 (Python Code)

Max Activating Token Index: 667

Text #12

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.7101. Min Act: -0.0001

Data Index: 1381997 (Python Code)

Max Activating Token Index: 825

Text #13

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.6860. Min Act: -0.0001

Data Index: 1393159 (Python Code)

Max Activating Token Index: 716

Text #14

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1420956 (Python Code)

Max Activating Token Index: 908

Text #15

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.6784. Min Act: -0.0001

Data Index: 1431938 (Python Code)

Max Activating Token Index: 143

Text #16

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.5959. Min Act: -0.0001

Data Index: 1361249 (Python Code)

Max Activating Token Index: 273

Text #17

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1380276 (Python Code)

Max Activating Token Index: 965

Text #18

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.6036. Min Act: -0.0001

Data Index: 1567229 (Python Code)

Max Activating Token Index: 643

Text #19

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.6369. Min Act: -0.0001

Data Index: 1532385 (Python Code)

Max Activating Token Index: 388