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

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

Neuron 4378 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1490. Min Act: -0.0000

Data Index: 1370759 (Python Code)

Max Activating Token Index: 966

Text #1

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1431. Min Act: -0.0000

Data Index: 1609490 (Python Code)

Max Activating Token Index: 626

Text #2

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1332. Min Act: -0.0000

Data Index: 1016192 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1280. Min Act: -0.0000

Data Index: 349406 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1348. Min Act: -0.0000

Data Index: 724195 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1183. Min Act: -0.0000

Data Index: 875856 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1152. Min Act: -0.0000

Data Index: 1518100 (Python Code)

Max Activating Token Index: 395

Text #7

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1077. Min Act: -0.0000

Data Index: 1634296 (Python Code)

Max Activating Token Index: 607

Text #8

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1068. Min Act: -0.0000

Data Index: 370183 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1171. Min Act: -0.0000

Data Index: 1407220 (Python Code)

Max Activating Token Index: 781

Text #10

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0991. Min Act: -0.0000

Data Index: 262546 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0930. Min Act: -0.0000

Data Index: 1465211 (Python Code)

Max Activating Token Index: 931

Text #12

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1091. Min Act: -0.0000

Data Index: 1458094 (Python Code)

Max Activating Token Index: 805

Text #13

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0994. Min Act: -0.0000

Data Index: 301901 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0907. Min Act: -0.0000

Data Index: 70327 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1038. Min Act: -0.0000

Data Index: 1537452 (Python Code)

Max Activating Token Index: 990

Text #16

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1627135 (Python Code)

Max Activating Token Index: 323

Text #17

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1055. Min Act: -0.0000

Data Index: 1530161 (Python Code)

Max Activating Token Index: 830

Text #18

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1420001 (Python Code)

Max Activating Token Index: 1000

Text #19

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0942. Min Act: -0.0000

Data Index: 1440377 (Python Code)

Max Activating Token Index: 362