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

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

Neuron 351 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3669. Min Range: -1.3669

Max Act: 1.3669. Min Act: -0.0001

Data Index: 613936 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 1.3669. Min Range: -1.3669

Max Act: 1.2391. Min Act: -0.0001

Data Index: 1147257 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 1.3669. Min Range: -1.3669

Max Act: 1.0855. Min Act: -0.0000

Data Index: 433496 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 1.3669. Min Range: -1.3669

Max Act: 1.0573. Min Act: -0.0001

Data Index: 248468 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 1.3669. Min Range: -1.3669

Max Act: 1.0011. Min Act: -0.0001

Data Index: 222925 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 1.3669. Min Range: -1.3669

Max Act: 0.9880. Min Act: -0.0001

Data Index: 1314142 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 1.3669. Min Range: -1.3669

Max Act: 0.9769. Min Act: -0.0001

Data Index: 1240804 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 1.3669. Min Range: -1.3669

Max Act: 1.0063. Min Act: -0.0000

Data Index: 332569 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 1.3669. Min Range: -1.3669

Max Act: 0.9758. Min Act: -0.0001

Data Index: 891787 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 1.3669. Min Range: -1.3669

Max Act: 0.9677. Min Act: -0.0001

Data Index: 988383 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 1.3669. Min Range: -1.3669

Max Act: 0.9547. Min Act: -0.0001

Data Index: 89031 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 1.3669. Min Range: -1.3669

Max Act: 0.9463. Min Act: -0.0001

Data Index: 771997 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 1.3669. Min Range: -1.3669

Max Act: 0.9084. Min Act: -0.0001

Data Index: 681270 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 1.3669. Min Range: -1.3669

Max Act: 0.9593. Min Act: -0.0001

Data Index: 1136467 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 1.3669. Min Range: -1.3669

Max Act: 0.9030. Min Act: -0.0001

Data Index: 761317 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 1.3669. Min Range: -1.3669

Max Act: 0.9744. Min Act: -0.0001

Data Index: 651184 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 1.3669. Min Range: -1.3669

Max Act: 0.9045. Min Act: -0.0000

Data Index: 158734 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 1.3669. Min Range: -1.3669

Max Act: 0.8888. Min Act: -0.0001

Data Index: 1193744 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 1.3669. Min Range: -1.3669

Max Act: 0.9249. Min Act: -0.0001

Data Index: 1122109 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 1.3669. Min Range: -1.3669

Max Act: 0.9333. Min Act: -0.0001

Data Index: 39330 (C4 (Web Text))

Max Activating Token Index: 596