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

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

Neuron 5984 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: 4.3839. Min Range: -4.3839

Max Act: 3.9588. Min Act: -0.0000

Data Index: 664701 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 4.3839. Min Range: -4.3839

Max Act: 3.8670. Min Act: -0.0000

Data Index: 815014 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 4.3839. Min Range: -4.3839

Max Act: 4.3839. Min Act: -0.0000

Data Index: 810586 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 4.3839. Min Range: -4.3839

Max Act: 3.7534. Min Act: -0.0000

Data Index: 300136 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 4.3839. Min Range: -4.3839

Max Act: 3.5377. Min Act: -0.0000

Data Index: 328243 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 4.3839. Min Range: -4.3839

Max Act: 3.4913. Min Act: -0.0000

Data Index: 75971 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 4.3839. Min Range: -4.3839

Max Act: 3.6840. Min Act: -0.0000

Data Index: 87401 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 4.3839. Min Range: -4.3839

Max Act: 3.3346. Min Act: -0.0000

Data Index: 1137172 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 4.3839. Min Range: -4.3839

Max Act: 3.4498. Min Act: -0.0000

Data Index: 119964 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 4.3839. Min Range: -4.3839

Max Act: 3.2224. Min Act: -0.0000

Data Index: 216365 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 4.3839. Min Range: -4.3839

Max Act: 3.3594. Min Act: -0.0000

Data Index: 868956 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 4.3839. Min Range: -4.3839

Max Act: 3.3012. Min Act: -0.0000

Data Index: 1071545 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 4.3839. Min Range: -4.3839

Max Act: 3.5869. Min Act: -0.0000

Data Index: 207344 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 4.3839. Min Range: -4.3839

Max Act: 3.1430. Min Act: -0.0000

Data Index: 335632 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 4.3839. Min Range: -4.3839

Max Act: 3.2893. Min Act: -0.0000

Data Index: 378848 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 4.3839. Min Range: -4.3839

Max Act: 3.3446. Min Act: -0.0000

Data Index: 799331 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 4.3839. Min Range: -4.3839

Max Act: 3.2007. Min Act: -0.0000

Data Index: 13933 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 4.3839. Min Range: -4.3839

Max Act: 2.9051. Min Act: -0.0000

Data Index: 271369 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 4.3839. Min Range: -4.3839

Max Act: 3.0165. Min Act: -0.0000

Data Index: 1127888 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 4.3839. Min Range: -4.3839

Max Act: 3.1579. Min Act: -0.0000

Data Index: 603217 (C4 (Web Text))

Max Activating Token Index: 650