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

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

Neuron 5889 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.0348. Min Range: -5.0348

Max Act: 5.0348. Min Act: -0.0000

Data Index: 741209 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 5.0348. Min Range: -5.0348

Max Act: 4.7794. Min Act: -0.0000

Data Index: 591241 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 5.0348. Min Range: -5.0348

Max Act: 4.8679. Min Act: -0.0000

Data Index: 778173 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 5.0348. Min Range: -5.0348

Max Act: 4.2953. Min Act: -0.0000

Data Index: 819606 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 5.0348. Min Range: -5.0348

Max Act: 4.8227. Min Act: -0.0000

Data Index: 349599 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 5.0348. Min Range: -5.0348

Max Act: 4.7633. Min Act: -0.0000

Data Index: 902305 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 5.0348. Min Range: -5.0348

Max Act: 4.8258. Min Act: -0.0000

Data Index: 605133 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 5.0348. Min Range: -5.0348

Max Act: 4.4600. Min Act: -0.0000

Data Index: 1287047 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 5.0348. Min Range: -5.0348

Max Act: 4.2593. Min Act: -0.0000

Data Index: 325810 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 5.0348. Min Range: -5.0348

Max Act: 4.1872. Min Act: -0.0000

Data Index: 416864 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 5.0348. Min Range: -5.0348

Max Act: 4.3303. Min Act: -0.0000

Data Index: 442922 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 5.0348. Min Range: -5.0348

Max Act: 4.1154. Min Act: -0.0000

Data Index: 891537 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 5.0348. Min Range: -5.0348

Max Act: 4.2753. Min Act: -0.0000

Data Index: 348072 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 5.0348. Min Range: -5.0348

Max Act: 3.9252. Min Act: -0.0000

Data Index: 822024 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 5.0348. Min Range: -5.0348

Max Act: 3.8096. Min Act: -0.0000

Data Index: 40414 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 5.0348. Min Range: -5.0348

Max Act: 3.7816. Min Act: -0.0000

Data Index: 447902 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 5.0348. Min Range: -5.0348

Max Act: 3.8950. Min Act: -0.0000

Data Index: 210671 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 5.0348. Min Range: -5.0348

Max Act: 3.8958. Min Act: -0.0000

Data Index: 429372 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 5.0348. Min Range: -5.0348

Max Act: 3.8714. Min Act: -0.0000

Data Index: 180535 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 5.0348. Min Range: -5.0348

Max Act: 3.7798. Min Act: -0.0000

Data Index: 262612 (C4 (Web Text))

Max Activating Token Index: 549