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

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

Neuron 3786 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2449. Min Act: -0.0001

Data Index: 913015 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2331. Min Act: -0.0001

Data Index: 116041 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2207. Min Act: -0.0001

Data Index: 1141110 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1987. Min Act: -0.0001

Data Index: 787079 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2148. Min Act: -0.0001

Data Index: 276368 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2078. Min Act: -0.0001

Data Index: 778934 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1928. Min Act: -0.0001

Data Index: 1173604 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1906. Min Act: -0.0001

Data Index: 789169 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1824. Min Act: -0.0001

Data Index: 1091559 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1943. Min Act: -0.0001

Data Index: 966951 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1765. Min Act: -0.0001

Data Index: 225843 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2096. Min Act: -0.0001

Data Index: 22344 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1952. Min Act: -0.0001

Data Index: 971276 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1937. Min Act: -0.0001

Data Index: 49511 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1944. Min Act: -0.0001

Data Index: 347173 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2001. Min Act: -0.0001

Data Index: 12783 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1918. Min Act: -0.0001

Data Index: 428712 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1856. Min Act: -0.0001

Data Index: 1147929 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1856. Min Act: -0.0001

Data Index: 36133 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1782. Min Act: -0.0001

Data Index: 727127 (C4 (Web Text))

Max Activating Token Index: 394