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

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

Neuron 3682 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: 1.9927. Min Range: -1.9927

Max Act: 1.9927. Min Act: -0.0001

Data Index: 353087 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.5821. Min Act: -0.0000

Data Index: 722535 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.7250. Min Act: -0.0001

Data Index: 973505 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.4909. Min Act: -0.0001

Data Index: 618040 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.3366. Min Act: -0.0001

Data Index: 784531 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.5798. Min Act: -0.0001

Data Index: 1346563 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.6444. Min Act: -0.0001

Data Index: 956924 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.4074. Min Act: -0.0001

Data Index: 561152 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.4937. Min Act: -0.0000

Data Index: 1284346 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.5598. Min Act: -0.0001

Data Index: 1006976 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.3875. Min Act: -0.0001

Data Index: 634856 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.5424. Min Act: -0.0001

Data Index: 587908 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.2671. Min Act: -0.0001

Data Index: 221105 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.5335. Min Act: -0.0000

Data Index: 1646952 (Python Code)

Max Activating Token Index: 37

Text #14

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.5257. Min Act: -0.0001

Data Index: 214820 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.3767. Min Act: -0.0001

Data Index: 932618 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.2652. Min Act: -0.0001

Data Index: 1119196 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.3375. Min Act: -0.0001

Data Index: 1108438 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.2186. Min Act: -0.0001

Data Index: 867698 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.3990. Min Act: -0.0000

Data Index: 1580325 (Python Code)

Max Activating Token Index: 59