Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2718 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.3049. Min Act: -0.0001

Data Index: 738090 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2437. Min Act: -0.0001

Data Index: 762052 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2670. Min Act: -0.0001

Data Index: 1244014 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2584. Min Act: -0.0001

Data Index: 945062 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2600. Min Act: -0.0001

Data Index: 1061429 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2439. Min Act: -0.0001

Data Index: 466062 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2501. Min Act: -0.0001

Data Index: 65843 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2226. Min Act: -0.0001

Data Index: 1291657 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2375. Min Act: -0.0001

Data Index: 367855 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.1950. Min Act: -0.0001

Data Index: 912065 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2193. Min Act: -0.0001

Data Index: 941763 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2323. Min Act: -0.0001

Data Index: 1004801 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2213. Min Act: -0.0001

Data Index: 671734 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2093. Min Act: -0.0001

Data Index: 927539 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2121. Min Act: -0.0001

Data Index: 417868 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2033. Min Act: -0.0001

Data Index: 1171688 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.1838. Min Act: -0.0001

Data Index: 956841 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2089. Min Act: -0.0001

Data Index: 995521 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.1842. Min Act: -0.0001

Data Index: 982303 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2041. Min Act: -0.0001

Data Index: 463266 (C4 (Web Text))

Max Activating Token Index: 25