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

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

Neuron 2070 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2627. Min Range: -0.2627

Max Act: 0.2627. Min Act: -0.0001

Data Index: 1021582 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 0.2627. Min Range: -0.2627

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1281847 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 0.2627. Min Range: -0.2627

Max Act: 0.2259. Min Act: -0.0001

Data Index: 612942 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.2627. Min Range: -0.2627

Max Act: 0.2120. Min Act: -0.0001

Data Index: 1483199 (Python Code)

Max Activating Token Index: 802

Text #4

Max Range: 0.2627. Min Range: -0.2627

Max Act: 0.2096. Min Act: -0.0000

Data Index: 103630 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.2627. Min Range: -0.2627

Max Act: 0.2135. Min Act: -0.0000

Data Index: 1652817 (Python Code)

Max Activating Token Index: 748

Text #6

Max Range: 0.2627. Min Range: -0.2627

Max Act: 0.2211. Min Act: -0.0000

Data Index: 1566076 (Python Code)

Max Activating Token Index: 686

Text #7

Max Range: 0.2627. Min Range: -0.2627

Max Act: 0.1949. Min Act: -0.0000

Data Index: 1054636 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.2627. Min Range: -0.2627

Max Act: 0.2117. Min Act: -0.0000

Data Index: 11280 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.2627. Min Range: -0.2627

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1651336 (Python Code)

Max Activating Token Index: 356

Text #10

Max Range: 0.2627. Min Range: -0.2627

Max Act: 0.1932. Min Act: -0.0001

Data Index: 370440 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.2627. Min Range: -0.2627

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1444970 (Python Code)

Max Activating Token Index: 198

Text #12

Max Range: 0.2627. Min Range: -0.2627

Max Act: 0.1872. Min Act: -0.0000

Data Index: 402004 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.2627. Min Range: -0.2627

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1432325 (Python Code)

Max Activating Token Index: 433

Text #14

Max Range: 0.2627. Min Range: -0.2627

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1625917 (Python Code)

Max Activating Token Index: 106

Text #15

Max Range: 0.2627. Min Range: -0.2627

Max Act: 0.2026. Min Act: -0.0000

Data Index: 1443100 (Python Code)

Max Activating Token Index: 869

Text #16

Max Range: 0.2627. Min Range: -0.2627

Max Act: 0.1769. Min Act: -0.0000

Data Index: 898077 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 0.2627. Min Range: -0.2627

Max Act: 0.1848. Min Act: -0.0000

Data Index: 1450092 (Python Code)

Max Activating Token Index: 119

Text #18

Max Range: 0.2627. Min Range: -0.2627

Max Act: 0.1900. Min Act: -0.0000

Data Index: 205451 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.2627. Min Range: -0.2627

Max Act: 0.1759. Min Act: -0.0000

Data Index: 1011489 (C4 (Web Text))

Max Activating Token Index: 958