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

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

Neuron 1155 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2487. Min Act: -0.0000

Data Index: 1373987 (Python Code)

Max Activating Token Index: 207

Text #1

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2362. Min Act: -0.0000

Data Index: 1239300 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2482. Min Act: -0.0000

Data Index: 244349 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2317. Min Act: -0.0000

Data Index: 873042 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2149. Min Act: -0.0000

Data Index: 1021076 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1632847 (Python Code)

Max Activating Token Index: 835

Text #6

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2059. Min Act: -0.0000

Data Index: 72548 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2040. Min Act: -0.0000

Data Index: 1353503 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1445027 (Python Code)

Max Activating Token Index: 912

Text #9

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1990. Min Act: -0.0000

Data Index: 1265356 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2081. Min Act: -0.0000

Data Index: 511486 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2082. Min Act: -0.0000

Data Index: 692745 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2038. Min Act: -0.0000

Data Index: 431013 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1823. Min Act: -0.0000

Data Index: 487671 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1885. Min Act: -0.0000

Data Index: 820870 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1911. Min Act: -0.0000

Data Index: 226018 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1978. Min Act: -0.0000

Data Index: 653303 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1840. Min Act: -0.0000

Data Index: 1431656 (Python Code)

Max Activating Token Index: 449

Text #18

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1911. Min Act: -0.0000

Data Index: 696947 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1037180 (C4 (Web Text))

Max Activating Token Index: 806