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

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

Neuron 2136 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9346. Min Range: -1.9346

Max Act: 1.8888. Min Act: -0.0000

Data Index: 1247591 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 1.9346. Min Range: -1.9346

Max Act: 1.9346. Min Act: -0.0000

Data Index: 974040 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 1.9346. Min Range: -1.9346

Max Act: 1.8252. Min Act: -0.0000

Data Index: 1348782 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 1.9346. Min Range: -1.9346

Max Act: 1.5640. Min Act: -0.0000

Data Index: 1116201 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 1.9346. Min Range: -1.9346

Max Act: 1.6268. Min Act: -0.0000

Data Index: 84808 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 1.9346. Min Range: -1.9346

Max Act: 1.6290. Min Act: -0.0000

Data Index: 38645 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 1.9346. Min Range: -1.9346

Max Act: 1.6144. Min Act: -0.0000

Data Index: 1190333 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 1.9346. Min Range: -1.9346

Max Act: 1.6868. Min Act: -0.0000

Data Index: 794709 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 1.9346. Min Range: -1.9346

Max Act: 1.5744. Min Act: -0.0000

Data Index: 1337165 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 1.9346. Min Range: -1.9346

Max Act: 1.5389. Min Act: -0.0000

Data Index: 1017657 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 1.9346. Min Range: -1.9346

Max Act: 1.6039. Min Act: -0.0000

Data Index: 389999 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 1.9346. Min Range: -1.9346

Max Act: 1.5037. Min Act: -0.0000

Data Index: 709448 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 1.9346. Min Range: -1.9346

Max Act: 1.5050. Min Act: -0.0000

Data Index: 1013375 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 1.9346. Min Range: -1.9346

Max Act: 1.4150. Min Act: -0.0000

Data Index: 584736 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 1.9346. Min Range: -1.9346

Max Act: 1.5832. Min Act: -0.0000

Data Index: 365976 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 1.9346. Min Range: -1.9346

Max Act: 1.5741. Min Act: -0.0000

Data Index: 218821 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 1.9346. Min Range: -1.9346

Max Act: 1.3825. Min Act: -0.0000

Data Index: 791004 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 1.9346. Min Range: -1.9346

Max Act: 1.3715. Min Act: -0.0000

Data Index: 1248538 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 1.9346. Min Range: -1.9346

Max Act: 1.4298. Min Act: -0.0000

Data Index: 608294 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 1.9346. Min Range: -1.9346

Max Act: 1.3426. Min Act: -0.0000

Data Index: 397383 (C4 (Web Text))

Max Activating Token Index: 342