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

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

Neuron 1407 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: 1.7653. Min Range: -1.7653

Max Act: 1.7653. Min Act: -0.0000

Data Index: 624508 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 1.7653. Min Range: -1.7653

Max Act: 1.7510. Min Act: -0.0000

Data Index: 960226 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 1.7653. Min Range: -1.7653

Max Act: 1.5005. Min Act: -0.0000

Data Index: 70184 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 1.7653. Min Range: -1.7653

Max Act: 1.4212. Min Act: -0.0000

Data Index: 206745 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 1.7653. Min Range: -1.7653

Max Act: 1.4669. Min Act: -0.0000

Data Index: 43481 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 1.7653. Min Range: -1.7653

Max Act: 1.3979. Min Act: -0.0000

Data Index: 741363 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 1.7653. Min Range: -1.7653

Max Act: 1.4644. Min Act: -0.0000

Data Index: 208270 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 1.7653. Min Range: -1.7653

Max Act: 1.3307. Min Act: -0.0000

Data Index: 1167329 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 1.7653. Min Range: -1.7653

Max Act: 1.2870. Min Act: -0.0000

Data Index: 1454067 (Python Code)

Max Activating Token Index: 19

Text #9

Max Range: 1.7653. Min Range: -1.7653

Max Act: 1.2634. Min Act: -0.0000

Data Index: 506166 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 1.7653. Min Range: -1.7653

Max Act: 1.3277. Min Act: -0.0000

Data Index: 1116583 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 1.7653. Min Range: -1.7653

Max Act: 1.2403. Min Act: -0.0000

Data Index: 605081 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 1.7653. Min Range: -1.7653

Max Act: 1.1577. Min Act: -0.0000

Data Index: 200461 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 1.7653. Min Range: -1.7653

Max Act: 1.2138. Min Act: -0.0000

Data Index: 248788 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 1.7653. Min Range: -1.7653

Max Act: 1.2434. Min Act: -0.0000

Data Index: 1255633 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 1.7653. Min Range: -1.7653

Max Act: 1.1269. Min Act: -0.0000

Data Index: 549972 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 1.7653. Min Range: -1.7653

Max Act: 1.2978. Min Act: -0.0000

Data Index: 1098930 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 1.7653. Min Range: -1.7653

Max Act: 1.1891. Min Act: -0.0000

Data Index: 586911 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 1.7653. Min Range: -1.7653

Max Act: 1.2017. Min Act: -0.0000

Data Index: 789024 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 1.7653. Min Range: -1.7653

Max Act: 1.1963. Min Act: -0.0000

Data Index: 440860 (C4 (Web Text))

Max Activating Token Index: 863