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

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

Neuron 94 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: 2.1348. Min Range: -2.1348

Max Act: 1.9560. Min Act: -0.0000

Data Index: 232727 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 2.1348. Min Range: -2.1348

Max Act: 2.0055. Min Act: -0.0001

Data Index: 949054 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 2.1348. Min Range: -2.1348

Max Act: 1.8040. Min Act: -0.0000

Data Index: 1124881 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 2.1348. Min Range: -2.1348

Max Act: 1.7568. Min Act: -0.0000

Data Index: 14647 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 2.1348. Min Range: -2.1348

Max Act: 1.6936. Min Act: -0.0001

Data Index: 1316193 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 2.1348. Min Range: -2.1348

Max Act: 2.1348. Min Act: -0.0000

Data Index: 906579 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 2.1348. Min Range: -2.1348

Max Act: 1.7883. Min Act: -0.0000

Data Index: 610778 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 2.1348. Min Range: -2.1348

Max Act: 1.7639. Min Act: -0.0001

Data Index: 753159 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 2.1348. Min Range: -2.1348

Max Act: 1.8343. Min Act: -0.0000

Data Index: 536015 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 2.1348. Min Range: -2.1348

Max Act: 1.7465. Min Act: -0.0000

Data Index: 99384 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 2.1348. Min Range: -2.1348

Max Act: 1.6381. Min Act: -0.0001

Data Index: 278919 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 2.1348. Min Range: -2.1348

Max Act: 1.6216. Min Act: -0.0000

Data Index: 437915 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 2.1348. Min Range: -2.1348

Max Act: 1.7012. Min Act: -0.0000

Data Index: 669740 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 2.1348. Min Range: -2.1348

Max Act: 1.7269. Min Act: -0.0000

Data Index: 342640 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 2.1348. Min Range: -2.1348

Max Act: 1.7188. Min Act: -0.0000

Data Index: 904144 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 2.1348. Min Range: -2.1348

Max Act: 1.6614. Min Act: -0.0000

Data Index: 657638 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 2.1348. Min Range: -2.1348

Max Act: 1.4812. Min Act: -0.0000

Data Index: 701925 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 2.1348. Min Range: -2.1348

Max Act: 1.8314. Min Act: -0.0001

Data Index: 394392 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 2.1348. Min Range: -2.1348

Max Act: 1.5138. Min Act: -0.0000

Data Index: 1099038 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 2.1348. Min Range: -2.1348

Max Act: 1.5131. Min Act: -0.0000

Data Index: 85714 (C4 (Web Text))

Max Activating Token Index: 243