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

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

Neuron 573 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: 1.3041. Min Range: -1.3041

Max Act: 1.3041. Min Act: -0.0000

Data Index: 1579626 (Python Code)

Max Activating Token Index: 523

Text #1

Max Range: 1.3041. Min Range: -1.3041

Max Act: 1.2029. Min Act: -0.0000

Data Index: 707544 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 1.3041. Min Range: -1.3041

Max Act: 1.0923. Min Act: -0.0000

Data Index: 334275 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 1.3041. Min Range: -1.3041

Max Act: 1.1339. Min Act: -0.0000

Data Index: 1346031 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 1.3041. Min Range: -1.3041

Max Act: 1.1272. Min Act: -0.0000

Data Index: 1197422 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 1.3041. Min Range: -1.3041

Max Act: 1.0954. Min Act: -0.0000

Data Index: 1298338 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 1.3041. Min Range: -1.3041

Max Act: 1.0919. Min Act: -0.0000

Data Index: 1558087 (Python Code)

Max Activating Token Index: 159

Text #7

Max Range: 1.3041. Min Range: -1.3041

Max Act: 1.0826. Min Act: -0.0000

Data Index: 505661 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 1.3041. Min Range: -1.3041

Max Act: 1.0194. Min Act: -0.0000

Data Index: 1011111 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 1.3041. Min Range: -1.3041

Max Act: 1.1075. Min Act: -0.0000

Data Index: 1572786 (Python Code)

Max Activating Token Index: 655

Text #10

Max Range: 1.3041. Min Range: -1.3041

Max Act: 1.0883. Min Act: -0.0000

Data Index: 1449517 (Python Code)

Max Activating Token Index: 128

Text #11

Max Range: 1.3041. Min Range: -1.3041

Max Act: 1.0918. Min Act: -0.0000

Data Index: 891358 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 1.3041. Min Range: -1.3041

Max Act: 1.0274. Min Act: -0.0000

Data Index: 882015 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 1.3041. Min Range: -1.3041

Max Act: 1.0406. Min Act: -0.0000

Data Index: 447830 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 1.3041. Min Range: -1.3041

Max Act: 1.0077. Min Act: -0.0000

Data Index: 1616875 (Python Code)

Max Activating Token Index: 149

Text #15

Max Range: 1.3041. Min Range: -1.3041

Max Act: 1.0137. Min Act: -0.0000

Data Index: 1542250 (Python Code)

Max Activating Token Index: 7

Text #16

Max Range: 1.3041. Min Range: -1.3041

Max Act: 1.0035. Min Act: -0.0000

Data Index: 902163 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 1.3041. Min Range: -1.3041

Max Act: 0.9717. Min Act: -0.0000

Data Index: 1132356 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 1.3041. Min Range: -1.3041

Max Act: 1.0041. Min Act: -0.0000

Data Index: 746496 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 1.3041. Min Range: -1.3041

Max Act: 0.9993. Min Act: -0.0000

Data Index: 227322 (C4 (Web Text))

Max Activating Token Index: 217