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

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

Neuron 534 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.0985. Min Act: -0.0001

Data Index: 811782 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.1387. Min Act: -0.0001

Data Index: 927464 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.1400. Min Act: -0.0001

Data Index: 1191588 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.0986. Min Act: -0.0001

Data Index: 1228184 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.0595. Min Act: -0.0001

Data Index: 1256736 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.0483. Min Act: -0.0001

Data Index: 1050781 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.0028. Min Act: -0.0001

Data Index: 322867 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.0274. Min Act: -0.0001

Data Index: 1333500 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.0479. Min Act: -0.0001

Data Index: 1171061 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.0941. Min Act: -0.0001

Data Index: 685916 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.1281. Min Act: -0.0001

Data Index: 1137371 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.0883. Min Act: -0.0001

Data Index: 697471 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.0765. Min Act: -0.0001

Data Index: 798609 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.9754. Min Act: -0.0001

Data Index: 1065183 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.0497. Min Act: -0.0001

Data Index: 764274 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.0188. Min Act: -0.0001

Data Index: 31502 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.0506. Min Act: -0.0001

Data Index: 872072 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.9847. Min Act: -0.0001

Data Index: 604436 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.9820. Min Act: -0.0001

Data Index: 1176028 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.9131. Min Act: -0.0001

Data Index: 353448 (C4 (Web Text))

Max Activating Token Index: 572