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

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

Neuron 1432 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4075. Min Range: -2.4075

Max Act: 2.4075. Min Act: -0.0000

Data Index: 600516 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 2.4075. Min Range: -2.4075

Max Act: 2.4021. Min Act: -0.0000

Data Index: 226025 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 2.4075. Min Range: -2.4075

Max Act: 2.2597. Min Act: -0.0000

Data Index: 1217272 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 2.4075. Min Range: -2.4075

Max Act: 2.0961. Min Act: -0.0000

Data Index: 1236138 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 2.4075. Min Range: -2.4075

Max Act: 2.2914. Min Act: -0.0000

Data Index: 488005 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 2.4075. Min Range: -2.4075

Max Act: 1.8564. Min Act: -0.0000

Data Index: 195974 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 2.4075. Min Range: -2.4075

Max Act: 1.8651. Min Act: -0.0000

Data Index: 421637 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 2.4075. Min Range: -2.4075

Max Act: 1.9495. Min Act: -0.0000

Data Index: 1642599 (Python Code)

Max Activating Token Index: 240

Text #8

Max Range: 2.4075. Min Range: -2.4075

Max Act: 1.9897. Min Act: -0.0000

Data Index: 723310 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 2.4075. Min Range: -2.4075

Max Act: 1.9174. Min Act: -0.0000

Data Index: 590916 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 2.4075. Min Range: -2.4075

Max Act: 1.6589. Min Act: -0.0000

Data Index: 353203 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 2.4075. Min Range: -2.4075

Max Act: 1.7019. Min Act: -0.0000

Data Index: 772609 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 2.4075. Min Range: -2.4075

Max Act: 1.6632. Min Act: -0.0000

Data Index: 652647 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 2.4075. Min Range: -2.4075

Max Act: 1.8505. Min Act: -0.0000

Data Index: 273298 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 2.4075. Min Range: -2.4075

Max Act: 1.5220. Min Act: -0.0000

Data Index: 531125 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 2.4075. Min Range: -2.4075

Max Act: 1.5904. Min Act: -0.0000

Data Index: 538852 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 2.4075. Min Range: -2.4075

Max Act: 1.5937. Min Act: -0.0000

Data Index: 1224259 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 2.4075. Min Range: -2.4075

Max Act: 1.6107. Min Act: -0.0000

Data Index: 339677 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 2.4075. Min Range: -2.4075

Max Act: 1.6754. Min Act: -0.0000

Data Index: 1373862 (Python Code)

Max Activating Token Index: 567

Text #19

Max Range: 2.4075. Min Range: -2.4075

Max Act: 1.6314. Min Act: -0.0000

Data Index: 616638 (C4 (Web Text))

Max Activating Token Index: 836