Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 376 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5835. Min Range: -1.5835

Max Act: 1.5835. Min Act: -0.0000

Data Index: 836890 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 1.5835. Min Range: -1.5835

Max Act: 1.2915. Min Act: -0.0000

Data Index: 1284400 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 1.5835. Min Range: -1.5835

Max Act: 1.2848. Min Act: -0.0000

Data Index: 1182901 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 1.5835. Min Range: -1.5835

Max Act: 1.2928. Min Act: -0.0000

Data Index: 396832 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 1.5835. Min Range: -1.5835

Max Act: 1.3289. Min Act: -0.0000

Data Index: 657657 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 1.5835. Min Range: -1.5835

Max Act: 1.2587. Min Act: -0.0000

Data Index: 1178720 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 1.5835. Min Range: -1.5835

Max Act: 1.2611. Min Act: -0.0000

Data Index: 165322 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 1.5835. Min Range: -1.5835

Max Act: 1.1924. Min Act: -0.0000

Data Index: 584249 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 1.5835. Min Range: -1.5835

Max Act: 1.1899. Min Act: -0.0000

Data Index: 920817 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 1.5835. Min Range: -1.5835

Max Act: 1.1986. Min Act: -0.0000

Data Index: 301386 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 1.5835. Min Range: -1.5835

Max Act: 1.2276. Min Act: -0.0000

Data Index: 527084 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 1.5835. Min Range: -1.5835

Max Act: 1.2080. Min Act: -0.0000

Data Index: 251473 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 1.5835. Min Range: -1.5835

Max Act: 1.1165. Min Act: -0.0000

Data Index: 64141 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 1.5835. Min Range: -1.5835

Max Act: 1.1490. Min Act: -0.0000

Data Index: 1175779 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 1.5835. Min Range: -1.5835

Max Act: 1.1847. Min Act: -0.0000

Data Index: 279719 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 1.5835. Min Range: -1.5835

Max Act: 1.1354. Min Act: -0.0000

Data Index: 1642507 (Python Code)

Max Activating Token Index: 749

Text #16

Max Range: 1.5835. Min Range: -1.5835

Max Act: 1.1365. Min Act: -0.0000

Data Index: 1435625 (Python Code)

Max Activating Token Index: 725

Text #17

Max Range: 1.5835. Min Range: -1.5835

Max Act: 1.1327. Min Act: -0.0000

Data Index: 807252 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 1.5835. Min Range: -1.5835

Max Act: 1.1090. Min Act: -0.0000

Data Index: 1418531 (Python Code)

Max Activating Token Index: 2

Text #19

Max Range: 1.5835. Min Range: -1.5835

Max Act: 1.1186. Min Act: -0.0000

Data Index: 1499045 (Python Code)

Max Activating Token Index: 371