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

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

Neuron 1460 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.5975. Min Act: -0.0000

Data Index: 216283 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.4935. Min Act: -0.0000

Data Index: 1531 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.4747. Min Act: -0.0000

Data Index: 752598 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.4377. Min Act: -0.0000

Data Index: 1158918 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1214281 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.4275. Min Act: -0.0000

Data Index: 386746 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.3895. Min Act: -0.0000

Data Index: 9018 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.3874. Min Act: -0.0000

Data Index: 397965 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.3812. Min Act: -0.0000

Data Index: 1284853 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.3867. Min Act: -0.0000

Data Index: 197527 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.3654. Min Act: -0.0000

Data Index: 32046 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.3610. Min Act: -0.0000

Data Index: 428280 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.3703. Min Act: 0.0000

Data Index: 980319 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.3342. Min Act: -0.0000

Data Index: 289133 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.3360. Min Act: -0.0000

Data Index: 784277 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.3183. Min Act: -0.0000

Data Index: 902607 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.3161. Min Act: -0.0000

Data Index: 1141861 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.3263. Min Act: -0.0000

Data Index: 989009 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.2975. Min Act: -0.0000

Data Index: 1050214 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.2804. Min Act: -0.0000

Data Index: 241313 (C4 (Web Text))

Max Activating Token Index: 219