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

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

Neuron 1142 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.3198. Min Act: -0.0000

Data Index: 1579940 (Python Code)

Max Activating Token Index: 783

Text #1

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.3040. Min Act: 0.0000

Data Index: 1503562 (Python Code)

Max Activating Token Index: 298

Text #2

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2767. Min Act: -0.0000

Data Index: 701446 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2230. Min Act: -0.0000

Data Index: 629015 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2223. Min Act: -0.0000

Data Index: 240217 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2203. Min Act: -0.0000

Data Index: 1573779 (Python Code)

Max Activating Token Index: 323

Text #6

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2073. Min Act: -0.0000

Data Index: 1634800 (Python Code)

Max Activating Token Index: 893

Text #7

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2143. Min Act: -0.0000

Data Index: 221687 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2121. Min Act: -0.0000

Data Index: 1608923 (Python Code)

Max Activating Token Index: 107

Text #9

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.1983. Min Act: -0.0000

Data Index: 1225419 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2206. Min Act: -0.0000

Data Index: 88657 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.1952. Min Act: -0.0000

Data Index: 1470007 (Python Code)

Max Activating Token Index: 774

Text #12

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2025. Min Act: -0.0000

Data Index: 856099 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.1865. Min Act: 0.0000

Data Index: 1418113 (Python Code)

Max Activating Token Index: 749

Text #14

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1390347 (Python Code)

Max Activating Token Index: 540

Text #15

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1446168 (Python Code)

Max Activating Token Index: 923

Text #16

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.1999. Min Act: -0.0000

Data Index: 1610754 (Python Code)

Max Activating Token Index: 733

Text #17

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.1927. Min Act: -0.0000

Data Index: 1575473 (Python Code)

Max Activating Token Index: 419

Text #18

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.1921. Min Act: 0.0000

Data Index: 146725 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.1890. Min Act: 0.0000

Data Index: 1526310 (Python Code)

Max Activating Token Index: 628