Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2467 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.3097. Min Act: -0.0001

Data Index: 743560 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.3062. Min Act: -0.0001

Data Index: 531051 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2696. Min Act: -0.0001

Data Index: 169122 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2478. Min Act: -0.0001

Data Index: 532175 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2829. Min Act: -0.0001

Data Index: 387696 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2509. Min Act: -0.0001

Data Index: 456566 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2553. Min Act: -0.0001

Data Index: 890128 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2588. Min Act: -0.0001

Data Index: 902620 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2222. Min Act: -0.0001

Data Index: 344326 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2031. Min Act: -0.0001

Data Index: 709795 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2410. Min Act: -0.0001

Data Index: 87005 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2387. Min Act: -0.0001

Data Index: 59269 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2320. Min Act: -0.0001

Data Index: 921769 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2384. Min Act: -0.0001

Data Index: 226550 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2284. Min Act: -0.0001

Data Index: 947114 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2278. Min Act: -0.0001

Data Index: 596585 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2166. Min Act: -0.0001

Data Index: 458163 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2394. Min Act: -0.0001

Data Index: 415638 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2356. Min Act: -0.0001

Data Index: 513986 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2110. Min Act: -0.0001

Data Index: 776348 (C4 (Web Text))

Max Activating Token Index: 432