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

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

Neuron 1608 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.2322. Min Act: -0.0003

Data Index: 745311 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.2169. Min Act: -0.0003

Data Index: 1019742 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.2117. Min Act: -0.0003

Data Index: 411665 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.2019. Min Act: -0.0003

Data Index: 1051592 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.2092. Min Act: -0.0003

Data Index: 262928 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.2075. Min Act: -0.0003

Data Index: 924451 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.2055. Min Act: -0.0003

Data Index: 1278803 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.2036. Min Act: -0.0003

Data Index: 663328 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.2130. Min Act: -0.0003

Data Index: 1311099 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1947. Min Act: -0.0003

Data Index: 411543 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1922. Min Act: -0.0003

Data Index: 315155 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1885. Min Act: -0.0003

Data Index: 1254706 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.2053. Min Act: -0.0003

Data Index: 974976 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1838. Min Act: -0.0003

Data Index: 420358 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1863. Min Act: -0.0003

Data Index: 140141 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1874. Min Act: -0.0003

Data Index: 1323228 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1880. Min Act: -0.0003

Data Index: 308736 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1932. Min Act: -0.0003

Data Index: 781812 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1989. Min Act: -0.0003

Data Index: 1317199 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1918. Min Act: -0.0003

Data Index: 1217503 (C4 (Web Text))

Max Activating Token Index: 173