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

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

Neuron 1899 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2354. Min Range: -1.2354

Max Act: 1.2354. Min Act: -0.0000

Data Index: 54541 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 1.2354. Min Range: -1.2354

Max Act: 1.1141. Min Act: -0.0000

Data Index: 682360 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 1.2354. Min Range: -1.2354

Max Act: 1.1734. Min Act: -0.0000

Data Index: 1369040 (Python Code)

Max Activating Token Index: 576

Text #3

Max Range: 1.2354. Min Range: -1.2354

Max Act: 0.9616. Min Act: -0.0000

Data Index: 1367017 (Python Code)

Max Activating Token Index: 186

Text #4

Max Range: 1.2354. Min Range: -1.2354

Max Act: 1.0019. Min Act: -0.0000

Data Index: 542738 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 1.2354. Min Range: -1.2354

Max Act: 0.8320. Min Act: -0.0000

Data Index: 517527 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 1.2354. Min Range: -1.2354

Max Act: 0.8727. Min Act: -0.0000

Data Index: 1429955 (Python Code)

Max Activating Token Index: 899

Text #7

Max Range: 1.2354. Min Range: -1.2354

Max Act: 0.8425. Min Act: -0.0000

Data Index: 466243 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 1.2354. Min Range: -1.2354

Max Act: 0.8667. Min Act: -0.0000

Data Index: 166389 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 1.2354. Min Range: -1.2354

Max Act: 0.8566. Min Act: -0.0000

Data Index: 1121880 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 1.2354. Min Range: -1.2354

Max Act: 0.8564. Min Act: 0.0000

Data Index: 654094 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 1.2354. Min Range: -1.2354

Max Act: 0.8502. Min Act: -0.0000

Data Index: 448467 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 1.2354. Min Range: -1.2354

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1278285 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 1.2354. Min Range: -1.2354

Max Act: 0.7993. Min Act: -0.0000

Data Index: 991506 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 1.2354. Min Range: -1.2354

Max Act: 0.8181. Min Act: -0.0000

Data Index: 1197971 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 1.2354. Min Range: -1.2354

Max Act: 0.7744. Min Act: -0.0000

Data Index: 724173 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 1.2354. Min Range: -1.2354

Max Act: 0.8051. Min Act: -0.0000

Data Index: 1110346 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 1.2354. Min Range: -1.2354

Max Act: 0.7382. Min Act: -0.0000

Data Index: 503971 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 1.2354. Min Range: -1.2354

Max Act: 0.8045. Min Act: -0.0000

Data Index: 438478 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 1.2354. Min Range: -1.2354

Max Act: 0.8436. Min Act: -0.0000

Data Index: 256119 (C4 (Web Text))

Max Activating Token Index: 321