Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4971 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.5761. Min Act: -0.0000

Data Index: 473733 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.4393. Min Act: -0.0000

Data Index: 937108 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1284763 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.3573. Min Act: -0.0000

Data Index: 542845 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.3426. Min Act: -0.0000

Data Index: 341499 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.2986. Min Act: -0.0000

Data Index: 224231 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1053267 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.2949. Min Act: -0.0000

Data Index: 193404 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.2801. Min Act: -0.0000

Data Index: 612020 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.2565. Min Act: -0.0000

Data Index: 160392 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.2366. Min Act: -0.0000

Data Index: 1160081 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.1925. Min Act: -0.0000

Data Index: 464680 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.2109. Min Act: -0.0000

Data Index: 181546 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.2247. Min Act: -0.0000

Data Index: 472934 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.2106. Min Act: -0.0000

Data Index: 1123624 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.2248. Min Act: -0.0000

Data Index: 273072 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.2110. Min Act: -0.0000

Data Index: 162552 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.2089. Min Act: -0.0000

Data Index: 559089 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.2073. Min Act: -0.0000

Data Index: 212095 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.2128. Min Act: -0.0000

Data Index: 970247 (C4 (Web Text))

Max Activating Token Index: 367