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

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

Neuron 1502 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.8950. Min Range: -8.8950

Max Act: 8.5434. Min Act: -0.0000

Data Index: 361152 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 8.8950. Min Range: -8.8950

Max Act: 8.5341. Min Act: -0.0000

Data Index: 999044 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 8.8950. Min Range: -8.8950

Max Act: 8.8950. Min Act: -0.0000

Data Index: 1021796 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 8.8950. Min Range: -8.8950

Max Act: 8.7252. Min Act: -0.0000

Data Index: 958088 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 8.8950. Min Range: -8.8950

Max Act: 8.5162. Min Act: -0.0000

Data Index: 890938 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 8.8950. Min Range: -8.8950

Max Act: 8.5231. Min Act: -0.0000

Data Index: 1256826 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 8.8950. Min Range: -8.8950

Max Act: 8.5430. Min Act: -0.0000

Data Index: 168274 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 8.8950. Min Range: -8.8950

Max Act: 8.3410. Min Act: -0.0000

Data Index: 544708 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 8.8950. Min Range: -8.8950

Max Act: 8.3417. Min Act: -0.0000

Data Index: 375668 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 8.8950. Min Range: -8.8950

Max Act: 8.4645. Min Act: -0.0000

Data Index: 366560 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 8.8950. Min Range: -8.8950

Max Act: 8.2611. Min Act: -0.0000

Data Index: 1238900 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 8.8950. Min Range: -8.8950

Max Act: 8.3780. Min Act: -0.0000

Data Index: 488999 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 8.8950. Min Range: -8.8950

Max Act: 8.5392. Min Act: -0.0000

Data Index: 80192 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 8.8950. Min Range: -8.8950

Max Act: 8.1943. Min Act: -0.0000

Data Index: 30253 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 8.8950. Min Range: -8.8950

Max Act: 8.0809. Min Act: -0.0000

Data Index: 1307558 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 8.8950. Min Range: -8.8950

Max Act: 8.2443. Min Act: -0.0000

Data Index: 956447 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 8.8950. Min Range: -8.8950

Max Act: 8.1957. Min Act: -0.0000

Data Index: 465078 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 8.8950. Min Range: -8.8950

Max Act: 8.3528. Min Act: -0.0000

Data Index: 1024264 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 8.8950. Min Range: -8.8950

Max Act: 8.1774. Min Act: -0.0000

Data Index: 1152764 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 8.8950. Min Range: -8.8950

Max Act: 8.1726. Min Act: -0.0000

Data Index: 1190460 (C4 (Web Text))

Max Activating Token Index: 529