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

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

Neuron 3611 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2481. Min Act: -0.0000

Data Index: 1115058 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1340224 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1944. Min Act: -0.0000

Data Index: 676269 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1923. Min Act: -0.0000

Data Index: 982545 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1995. Min Act: -0.0000

Data Index: 776585 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2059. Min Act: -0.0000

Data Index: 715888 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2033. Min Act: -0.0000

Data Index: 974847 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1707. Min Act: -0.0000

Data Index: 77681 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1960. Min Act: -0.0000

Data Index: 1310893 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2087. Min Act: -0.0000

Data Index: 787268 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1961. Min Act: -0.0000

Data Index: 771472 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1991. Min Act: -0.0000

Data Index: 959196 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1876. Min Act: -0.0000

Data Index: 648586 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1810. Min Act: -0.0001

Data Index: 290590 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1900. Min Act: -0.0000

Data Index: 396926 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1930. Min Act: -0.0000

Data Index: 48123 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1787. Min Act: -0.0000

Data Index: 1541093 (Python Code)

Max Activating Token Index: 690

Text #17

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1736. Min Act: -0.0000

Data Index: 1189785 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1908. Min Act: -0.0000

Data Index: 643268 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1676. Min Act: -0.0000

Data Index: 844126 (C4 (Web Text))

Max Activating Token Index: 418