Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2237 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4787. Min Act: -0.0003

Data Index: 1110183 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4529. Min Act: -0.0003

Data Index: 1166140 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4779. Min Act: -0.0003

Data Index: 1228472 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3965. Min Act: -0.0003

Data Index: 1301804 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4529. Min Act: -0.0003

Data Index: 37724 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3744. Min Act: -0.0003

Data Index: 588569 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4502. Min Act: -0.0003

Data Index: 171132 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4329. Min Act: -0.0003

Data Index: 633627 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4267. Min Act: -0.0003

Data Index: 343178 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3840. Min Act: -0.0003

Data Index: 60205 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4047. Min Act: -0.0003

Data Index: 876824 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4195. Min Act: -0.0003

Data Index: 135137 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4045. Min Act: -0.0003

Data Index: 887705 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4142. Min Act: -0.0003

Data Index: 639379 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4146. Min Act: -0.0003

Data Index: 455693 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3739. Min Act: -0.0003

Data Index: 890735 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3992. Min Act: -0.0003

Data Index: 1197245 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4306. Min Act: -0.0003

Data Index: 538651 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3860. Min Act: -0.0003

Data Index: 1340389 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3686. Min Act: -0.0003

Data Index: 474484 (C4 (Web Text))

Max Activating Token Index: 160