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

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

Neuron 1638 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: 0.9923. Min Range: -0.9923

Max Act: 0.9923. Min Act: -0.0001

Data Index: 947551 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.9762. Min Act: -0.0001

Data Index: 126545 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.9243. Min Act: -0.0001

Data Index: 1204869 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.8047. Min Act: -0.0001

Data Index: 448330 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.7316. Min Act: -0.0001

Data Index: 1203769 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.7677. Min Act: -0.0001

Data Index: 798799 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.8175. Min Act: -0.0001

Data Index: 451089 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.7012. Min Act: -0.0001

Data Index: 1263794 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.7275. Min Act: -0.0001

Data Index: 752867 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.7319. Min Act: -0.0001

Data Index: 90167 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.6849. Min Act: -0.0001

Data Index: 42365 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.7227. Min Act: -0.0001

Data Index: 90531 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.6960. Min Act: -0.0001

Data Index: 39589 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.6760. Min Act: -0.0001

Data Index: 1197798 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.6619. Min Act: -0.0001

Data Index: 848833 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.6824. Min Act: -0.0001

Data Index: 314587 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.6700. Min Act: -0.0001

Data Index: 1207105 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.6646. Min Act: -0.0001

Data Index: 1122864 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.6411. Min Act: -0.0001

Data Index: 1054826 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 0.9923. Min Range: -0.9923

Max Act: 0.6655. Min Act: -0.0001

Data Index: 473759 (C4 (Web Text))

Max Activating Token Index: 506