Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3033 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.7241. Min Act: -0.0000

Data Index: 1414782 (Python Code)

Max Activating Token Index: 209

Text #1

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6546. Min Act: -0.0001

Data Index: 1564286 (Python Code)

Max Activating Token Index: 983

Text #2

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6534. Min Act: -0.0001

Data Index: 1590324 (Python Code)

Max Activating Token Index: 476

Text #3

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6604. Min Act: -0.0001

Data Index: 1376678 (Python Code)

Max Activating Token Index: 321

Text #4

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.5941. Min Act: -0.0001

Data Index: 1560363 (Python Code)

Max Activating Token Index: 669

Text #5

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6217. Min Act: -0.0001

Data Index: 1404481 (Python Code)

Max Activating Token Index: 711

Text #6

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6253. Min Act: -0.0000

Data Index: 1499784 (Python Code)

Max Activating Token Index: 423

Text #7

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6201. Min Act: -0.0000

Data Index: 939361 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6342. Min Act: -0.0000

Data Index: 1194103 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6144. Min Act: -0.0001

Data Index: 1468945 (Python Code)

Max Activating Token Index: 741

Text #10

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.5757. Min Act: -0.0000

Data Index: 749113 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1627377 (Python Code)

Max Activating Token Index: 515

Text #12

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.5919. Min Act: -0.0000

Data Index: 1422382 (Python Code)

Max Activating Token Index: 1013

Text #13

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.5645. Min Act: -0.0000

Data Index: 1387112 (Python Code)

Max Activating Token Index: 482

Text #14

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.5635. Min Act: -0.0001

Data Index: 1603595 (Python Code)

Max Activating Token Index: 465

Text #15

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.5550. Min Act: -0.0001

Data Index: 717983 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.5712. Min Act: -0.0001

Data Index: 1410278 (Python Code)

Max Activating Token Index: 424

Text #17

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.5773. Min Act: -0.0001

Data Index: 1141555 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.5326. Min Act: -0.0000

Data Index: 1557359 (Python Code)

Max Activating Token Index: 582

Text #19

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.5583. Min Act: -0.0001

Data Index: 1486371 (Python Code)

Max Activating Token Index: 379