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

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

Neuron 4533 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: 0.1340. Min Range: -0.1340

Max Act: 0.1340. Min Act: -0.0001

Data Index: 1112490 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1334. Min Act: -0.0001

Data Index: 1139236 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1095. Min Act: -0.0001

Data Index: 1298243 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1259. Min Act: -0.0001

Data Index: 1209332 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0875. Min Act: -0.0001

Data Index: 596356 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0812. Min Act: -0.0001

Data Index: 760237 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0870. Min Act: -0.0001

Data Index: 163407 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0812. Min Act: -0.0001

Data Index: 877052 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0880. Min Act: -0.0001

Data Index: 80010 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0859. Min Act: -0.0001

Data Index: 735547 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0740. Min Act: -0.0001

Data Index: 1180864 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0822. Min Act: -0.0001

Data Index: 698852 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0738. Min Act: -0.0001

Data Index: 1015870 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0845. Min Act: -0.0001

Data Index: 555207 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0737. Min Act: -0.0000

Data Index: 914471 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1180800 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0735. Min Act: -0.0001

Data Index: 654885 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0706. Min Act: -0.0000

Data Index: 350853 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0716. Min Act: -0.0001

Data Index: 546875 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0712. Min Act: -0.0001

Data Index: 134265 (C4 (Web Text))

Max Activating Token Index: 356