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

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

Neuron 1971 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: 0.3632. Min Range: -0.3632

Max Act: 0.3632. Min Act: -0.0000

Data Index: 130750 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3611. Min Act: -0.0001

Data Index: 1320780 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2938. Min Act: -0.0000

Data Index: 696135 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2908. Min Act: -0.0001

Data Index: 829558 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2557. Min Act: -0.0001

Data Index: 1215421 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2279. Min Act: -0.0000

Data Index: 856153 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2201. Min Act: -0.0001

Data Index: 1197800 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2503. Min Act: -0.0001

Data Index: 362995 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2116. Min Act: -0.0000

Data Index: 1346194 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2043. Min Act: -0.0000

Data Index: 791288 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2078. Min Act: -0.0001

Data Index: 966706 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.1951. Min Act: -0.0001

Data Index: 1037073 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2033. Min Act: -0.0001

Data Index: 365959 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.1884. Min Act: -0.0001

Data Index: 251757 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.1925. Min Act: -0.0000

Data Index: 1079374 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.1755. Min Act: -0.0001

Data Index: 81685 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2062. Min Act: -0.0000

Data Index: 945920 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.1726. Min Act: -0.0001

Data Index: 839153 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.1798. Min Act: -0.0001

Data Index: 432070 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.1909. Min Act: -0.0000

Data Index: 573370 (C4 (Web Text))

Max Activating Token Index: 333