Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3077 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.5367. Min Act: -0.0001

Data Index: 565517 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3864. Min Act: -0.0001

Data Index: 896137 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3365. Min Act: -0.0001

Data Index: 1173088 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3137. Min Act: -0.0000

Data Index: 817438 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3361. Min Act: -0.0001

Data Index: 277213 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3036. Min Act: -0.0000

Data Index: 615381 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.2706. Min Act: -0.0000

Data Index: 212508 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.2603. Min Act: -0.0000

Data Index: 405965 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.2750. Min Act: -0.0000

Data Index: 154707 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.2748. Min Act: -0.0000

Data Index: 732442 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.2735. Min Act: -0.0001

Data Index: 554964 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.2636. Min Act: -0.0000

Data Index: 1597345 (Python Code)

Max Activating Token Index: 352

Text #12

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.1961. Min Act: -0.0001

Data Index: 1167722 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.2593. Min Act: -0.0000

Data Index: 28390 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.2520. Min Act: -0.0000

Data Index: 204497 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.2367. Min Act: -0.0000

Data Index: 565740 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.2095. Min Act: -0.0001

Data Index: 1148199 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.2738. Min Act: -0.0001

Data Index: 165531 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.2641. Min Act: -0.0001

Data Index: 271657 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.2552. Min Act: -0.0001

Data Index: 326644 (C4 (Web Text))

Max Activating Token Index: 966