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

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

Neuron 6133 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: 3.1930. Min Range: -3.1930

Max Act: 3.1930. Min Act: -0.0000

Data Index: 349819 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 3.1930. Min Range: -3.1930

Max Act: 2.4290. Min Act: -0.0000

Data Index: 1299071 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 3.1930. Min Range: -3.1930

Max Act: 2.3249. Min Act: -0.0000

Data Index: 1352254 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 3.1930. Min Range: -3.1930

Max Act: 2.3116. Min Act: -0.0000

Data Index: 377939 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 3.1930. Min Range: -3.1930

Max Act: 2.4116. Min Act: -0.0000

Data Index: 1478224 (Python Code)

Max Activating Token Index: 704

Text #5

Max Range: 3.1930. Min Range: -3.1930

Max Act: 2.2330. Min Act: -0.0000

Data Index: 1374360 (Python Code)

Max Activating Token Index: 592

Text #6

Max Range: 3.1930. Min Range: -3.1930

Max Act: 2.2385. Min Act: -0.0000

Data Index: 1577979 (Python Code)

Max Activating Token Index: 747

Text #7

Max Range: 3.1930. Min Range: -3.1930

Max Act: 2.2238. Min Act: -0.0000

Data Index: 420874 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 3.1930. Min Range: -3.1930

Max Act: 2.3351. Min Act: -0.0000

Data Index: 565058 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 3.1930. Min Range: -3.1930

Max Act: 2.0639. Min Act: -0.0000

Data Index: 813373 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 3.1930. Min Range: -3.1930

Max Act: 2.2840. Min Act: -0.0000

Data Index: 1459832 (Python Code)

Max Activating Token Index: 186

Text #11

Max Range: 3.1930. Min Range: -3.1930

Max Act: 2.2130. Min Act: -0.0000

Data Index: 1635740 (Python Code)

Max Activating Token Index: 792

Text #12

Max Range: 3.1930. Min Range: -3.1930

Max Act: 1.9890. Min Act: -0.0000

Data Index: 838251 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 3.1930. Min Range: -3.1930

Max Act: 2.0804. Min Act: -0.0000

Data Index: 869462 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 3.1930. Min Range: -3.1930

Max Act: 1.9666. Min Act: -0.0000

Data Index: 1021231 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 3.1930. Min Range: -3.1930

Max Act: 2.0060. Min Act: -0.0000

Data Index: 1433784 (Python Code)

Max Activating Token Index: 113

Text #16

Max Range: 3.1930. Min Range: -3.1930

Max Act: 1.8868. Min Act: -0.0000

Data Index: 613045 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 3.1930. Min Range: -3.1930

Max Act: 1.9768. Min Act: -0.0000

Data Index: 1454669 (Python Code)

Max Activating Token Index: 513

Text #18

Max Range: 3.1930. Min Range: -3.1930

Max Act: 1.9961. Min Act: -0.0000

Data Index: 1453057 (Python Code)

Max Activating Token Index: 868

Text #19

Max Range: 3.1930. Min Range: -3.1930

Max Act: 2.0755. Min Act: -0.0000

Data Index: 336944 (C4 (Web Text))

Max Activating Token Index: 917