Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2887 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1362. Min Range: -1.1362

Max Act: 1.0603. Min Act: -0.0001

Data Index: 730053 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 1.1362. Min Range: -1.1362

Max Act: 1.0841. Min Act: -0.0001

Data Index: 54841 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 1.1362. Min Range: -1.1362

Max Act: 1.1362. Min Act: -0.0001

Data Index: 941825 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 1.1362. Min Range: -1.1362

Max Act: 1.0714. Min Act: -0.0001

Data Index: 625024 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 1.1362. Min Range: -1.1362

Max Act: 0.9154. Min Act: -0.0001

Data Index: 984235 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 1.1362. Min Range: -1.1362

Max Act: 0.8703. Min Act: -0.0001

Data Index: 1238552 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 1.1362. Min Range: -1.1362

Max Act: 0.8492. Min Act: -0.0001

Data Index: 1001445 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 1.1362. Min Range: -1.1362

Max Act: 0.8496. Min Act: -0.0001

Data Index: 716683 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 1.1362. Min Range: -1.1362

Max Act: 0.8577. Min Act: -0.0001

Data Index: 1050297 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 1.1362. Min Range: -1.1362

Max Act: 0.8281. Min Act: -0.0001

Data Index: 1016003 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 1.1362. Min Range: -1.1362

Max Act: 0.8265. Min Act: -0.0001

Data Index: 339931 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 1.1362. Min Range: -1.1362

Max Act: 0.8246. Min Act: -0.0001

Data Index: 651001 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 1.1362. Min Range: -1.1362

Max Act: 0.8727. Min Act: -0.0001

Data Index: 470117 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 1.1362. Min Range: -1.1362

Max Act: 0.7999. Min Act: -0.0001

Data Index: 430918 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 1.1362. Min Range: -1.1362

Max Act: 0.8053. Min Act: -0.0001

Data Index: 156393 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 1.1362. Min Range: -1.1362

Max Act: 0.8567. Min Act: -0.0001

Data Index: 421489 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 1.1362. Min Range: -1.1362

Max Act: 0.7324. Min Act: -0.0001

Data Index: 570413 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 1.1362. Min Range: -1.1362

Max Act: 0.8558. Min Act: -0.0001

Data Index: 1061496 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 1.1362. Min Range: -1.1362

Max Act: 0.8390. Min Act: -0.0001

Data Index: 1118763 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 1.1362. Min Range: -1.1362

Max Act: 0.8379. Min Act: -0.0001

Data Index: 954268 (C4 (Web Text))

Max Activating Token Index: 692