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

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

Neuron 5035 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1956. Min Range: -1.1956

Max Act: 1.1956. Min Act: -0.0000

Data Index: 1436838 (Python Code)

Max Activating Token Index: 402

Text #1

Max Range: 1.1956. Min Range: -1.1956

Max Act: 1.0444. Min Act: -0.0000

Data Index: 1389136 (Python Code)

Max Activating Token Index: 708

Text #2

Max Range: 1.1956. Min Range: -1.1956

Max Act: 1.0159. Min Act: -0.0000

Data Index: 721399 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 1.1956. Min Range: -1.1956

Max Act: 0.9142. Min Act: -0.0000

Data Index: 1591519 (Python Code)

Max Activating Token Index: 827

Text #4

Max Range: 1.1956. Min Range: -1.1956

Max Act: 0.8828. Min Act: -0.0000

Data Index: 1518576 (Python Code)

Max Activating Token Index: 748

Text #5

Max Range: 1.1956. Min Range: -1.1956

Max Act: 0.8467. Min Act: -0.0000

Data Index: 688901 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 1.1956. Min Range: -1.1956

Max Act: 0.8808. Min Act: -0.0000

Data Index: 1538577 (Python Code)

Max Activating Token Index: 698

Text #7

Max Range: 1.1956. Min Range: -1.1956

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1630176 (Python Code)

Max Activating Token Index: 327

Text #8

Max Range: 1.1956. Min Range: -1.1956

Max Act: 0.8468. Min Act: -0.0000

Data Index: 1379677 (Python Code)

Max Activating Token Index: 640

Text #9

Max Range: 1.1956. Min Range: -1.1956

Max Act: 0.8212. Min Act: -0.0000

Data Index: 732602 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 1.1956. Min Range: -1.1956

Max Act: 0.7815. Min Act: -0.0000

Data Index: 437816 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 1.1956. Min Range: -1.1956

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1450840 (Python Code)

Max Activating Token Index: 193

Text #12

Max Range: 1.1956. Min Range: -1.1956

Max Act: 0.7418. Min Act: -0.0000

Data Index: 1366113 (Python Code)

Max Activating Token Index: 923

Text #13

Max Range: 1.1956. Min Range: -1.1956

Max Act: 0.7817. Min Act: -0.0000

Data Index: 901506 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 1.1956. Min Range: -1.1956

Max Act: 0.6968. Min Act: -0.0000

Data Index: 764310 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 1.1956. Min Range: -1.1956

Max Act: 0.7315. Min Act: -0.0000

Data Index: 1402781 (Python Code)

Max Activating Token Index: 790

Text #16

Max Range: 1.1956. Min Range: -1.1956

Max Act: 0.6953. Min Act: -0.0000

Data Index: 1169831 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 1.1956. Min Range: -1.1956

Max Act: 0.6481. Min Act: -0.0000

Data Index: 1532733 (Python Code)

Max Activating Token Index: 164

Text #18

Max Range: 1.1956. Min Range: -1.1956

Max Act: 0.6898. Min Act: -0.0000

Data Index: 1343200 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 1.1956. Min Range: -1.1956

Max Act: 0.6507. Min Act: -0.0000

Data Index: 1440358 (Python Code)

Max Activating Token Index: 30