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

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

Neuron 2734 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3236. Min Range: -1.3236

Max Act: 1.3236. Min Act: -0.0000

Data Index: 645699 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 1.3236. Min Range: -1.3236

Max Act: 1.1378. Min Act: -0.0000

Data Index: 113748 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 1.3236. Min Range: -1.3236

Max Act: 1.0370. Min Act: -0.0000

Data Index: 201153 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 1.3236. Min Range: -1.3236

Max Act: 1.0354. Min Act: -0.0000

Data Index: 623888 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 1.3236. Min Range: -1.3236

Max Act: 0.9566. Min Act: -0.0000

Data Index: 971443 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 1.3236. Min Range: -1.3236

Max Act: 0.9047. Min Act: -0.0000

Data Index: 1286849 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 1.3236. Min Range: -1.3236

Max Act: 0.9219. Min Act: -0.0000

Data Index: 178706 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 1.3236. Min Range: -1.3236

Max Act: 0.8693. Min Act: -0.0000

Data Index: 973875 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 1.3236. Min Range: -1.3236

Max Act: 0.9142. Min Act: -0.0000

Data Index: 797410 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 1.3236. Min Range: -1.3236

Max Act: 0.8316. Min Act: -0.0000

Data Index: 864461 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 1.3236. Min Range: -1.3236

Max Act: 0.8406. Min Act: -0.0000

Data Index: 75089 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 1.3236. Min Range: -1.3236

Max Act: 0.8056. Min Act: -0.0000

Data Index: 647555 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 1.3236. Min Range: -1.3236

Max Act: 0.8392. Min Act: -0.0000

Data Index: 745816 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 1.3236. Min Range: -1.3236

Max Act: 0.7574. Min Act: -0.0000

Data Index: 1424144 (Python Code)

Max Activating Token Index: 540

Text #14

Max Range: 1.3236. Min Range: -1.3236

Max Act: 0.7898. Min Act: -0.0000

Data Index: 716085 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 1.3236. Min Range: -1.3236

Max Act: 0.7610. Min Act: -0.0000

Data Index: 1050974 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 1.3236. Min Range: -1.3236

Max Act: 0.7422. Min Act: -0.0000

Data Index: 746318 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 1.3236. Min Range: -1.3236

Max Act: 0.7827. Min Act: -0.0000

Data Index: 989314 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 1.3236. Min Range: -1.3236

Max Act: 0.7526. Min Act: -0.0000

Data Index: 1397863 (Python Code)

Max Activating Token Index: 702

Text #19

Max Range: 1.3236. Min Range: -1.3236

Max Act: 0.8019. Min Act: -0.0000

Data Index: 517491 (C4 (Web Text))

Max Activating Token Index: 306