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

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

Neuron 1802 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: 0.9065. Min Range: -0.9065

Max Act: 0.9065. Min Act: -0.0003

Data Index: 638855 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.8540. Min Act: -0.0003

Data Index: 856319 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.8234. Min Act: -0.0003

Data Index: 614311 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.8193. Min Act: -0.0003

Data Index: 1330937 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.8156. Min Act: -0.0003

Data Index: 1005357 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.8098. Min Act: -0.0003

Data Index: 133812 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.8113. Min Act: -0.0003

Data Index: 985444 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.8539. Min Act: -0.0003

Data Index: 353972 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7298. Min Act: -0.0003

Data Index: 244263 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.8227. Min Act: -0.0003

Data Index: 448931 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.8184. Min Act: -0.0003

Data Index: 305223 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7571. Min Act: -0.0003

Data Index: 334927 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7829. Min Act: -0.0003

Data Index: 559198 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7432. Min Act: -0.0003

Data Index: 556241 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7548. Min Act: -0.0003

Data Index: 272666 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7579. Min Act: -0.0003

Data Index: 531382 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7916. Min Act: -0.0003

Data Index: 1242664 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7195. Min Act: -0.0003

Data Index: 839847 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7564. Min Act: -0.0003

Data Index: 1340334 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.6903. Min Act: -0.0003

Data Index: 1229659 (C4 (Web Text))

Max Activating Token Index: 812