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

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

Neuron 3908 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.6508. Min Act: -0.0000

Data Index: 246572 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5796. Min Act: -0.0000

Data Index: 1274361 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1245463 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4955. Min Act: -0.0000

Data Index: 311531 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4816. Min Act: -0.0000

Data Index: 1046909 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.3875. Min Act: -0.0000

Data Index: 541716 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4506. Min Act: -0.0000

Data Index: 8881 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4485. Min Act: -0.0000

Data Index: 779551 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1273361 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4471. Min Act: -0.0000

Data Index: 917577 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4277. Min Act: -0.0000

Data Index: 961587 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4234. Min Act: -0.0000

Data Index: 173750 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1150534 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4368. Min Act: -0.0000

Data Index: 59856 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4454. Min Act: -0.0000

Data Index: 7593 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4214. Min Act: -0.0000

Data Index: 10227 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4345. Min Act: -0.0000

Data Index: 1017734 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1058120 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.3992. Min Act: -0.0000

Data Index: 95132 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.3972. Min Act: -0.0000

Data Index: 841882 (C4 (Web Text))

Max Activating Token Index: 264