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

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

Neuron 2472 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: 0.5079. Min Range: -0.5079

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1001431 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4907. Min Act: -0.0000

Data Index: 983812 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4675. Min Act: -0.0000

Data Index: 412788 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1127358 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3542. Min Act: -0.0000

Data Index: 143876 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4012. Min Act: -0.0000

Data Index: 382840 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3896. Min Act: -0.0000

Data Index: 182727 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3456. Min Act: -0.0000

Data Index: 86804 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3328. Min Act: -0.0000

Data Index: 720168 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1183428 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3497. Min Act: -0.0000

Data Index: 1522581 (Python Code)

Max Activating Token Index: 525

Text #11

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3533. Min Act: -0.0000

Data Index: 948678 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3590. Min Act: -0.0000

Data Index: 1311138 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3361. Min Act: -0.0000

Data Index: 266291 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3342. Min Act: -0.0000

Data Index: 293912 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3007. Min Act: -0.0000

Data Index: 575343 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3273. Min Act: -0.0000

Data Index: 744419 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3119. Min Act: -0.0000

Data Index: 368073 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3019. Min Act: -0.0000

Data Index: 1221374 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3012. Min Act: -0.0000

Data Index: 561117 (C4 (Web Text))

Max Activating Token Index: 861