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

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

Neuron 1947 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: 1.8649. Min Range: -1.8649

Max Act: 1.8115. Min Act: -0.0001

Data Index: 1474078 (Python Code)

Max Activating Token Index: 245

Text #1

Max Range: 1.8649. Min Range: -1.8649

Max Act: 1.8649. Min Act: -0.0001

Data Index: 1602072 (Python Code)

Max Activating Token Index: 506

Text #2

Max Range: 1.8649. Min Range: -1.8649

Max Act: 1.6100. Min Act: -0.0001

Data Index: 1488254 (Python Code)

Max Activating Token Index: 619

Text #3

Max Range: 1.8649. Min Range: -1.8649

Max Act: 1.7416. Min Act: -0.0001

Data Index: 1562278 (Python Code)

Max Activating Token Index: 543

Text #4

Max Range: 1.8649. Min Range: -1.8649

Max Act: 1.5566. Min Act: -0.0001

Data Index: 1596064 (Python Code)

Max Activating Token Index: 269

Text #5

Max Range: 1.8649. Min Range: -1.8649

Max Act: 1.4774. Min Act: -0.0001

Data Index: 1561384 (Python Code)

Max Activating Token Index: 879

Text #6

Max Range: 1.8649. Min Range: -1.8649

Max Act: 1.5132. Min Act: -0.0001

Data Index: 1522540 (Python Code)

Max Activating Token Index: 676

Text #7

Max Range: 1.8649. Min Range: -1.8649

Max Act: 1.4434. Min Act: -0.0001

Data Index: 1591954 (Python Code)

Max Activating Token Index: 323

Text #8

Max Range: 1.8649. Min Range: -1.8649

Max Act: 1.4397. Min Act: -0.0001

Data Index: 1520314 (Python Code)

Max Activating Token Index: 364

Text #9

Max Range: 1.8649. Min Range: -1.8649

Max Act: 1.5327. Min Act: -0.0001

Data Index: 1596451 (Python Code)

Max Activating Token Index: 427

Text #10

Max Range: 1.8649. Min Range: -1.8649

Max Act: 1.3622. Min Act: -0.0001

Data Index: 1515487 (Python Code)

Max Activating Token Index: 451

Text #11

Max Range: 1.8649. Min Range: -1.8649

Max Act: 1.2862. Min Act: -0.0001

Data Index: 1581219 (Python Code)

Max Activating Token Index: 786

Text #12

Max Range: 1.8649. Min Range: -1.8649

Max Act: 1.3609. Min Act: -0.0001

Data Index: 1545116 (Python Code)

Max Activating Token Index: 1003

Text #13

Max Range: 1.8649. Min Range: -1.8649

Max Act: 1.4233. Min Act: -0.0001

Data Index: 1623200 (Python Code)

Max Activating Token Index: 911

Text #14

Max Range: 1.8649. Min Range: -1.8649

Max Act: 1.1603. Min Act: -0.0001

Data Index: 1511158 (Python Code)

Max Activating Token Index: 809

Text #15

Max Range: 1.8649. Min Range: -1.8649

Max Act: 1.2636. Min Act: -0.0001

Data Index: 1415621 (Python Code)

Max Activating Token Index: 199

Text #16

Max Range: 1.8649. Min Range: -1.8649

Max Act: 1.2522. Min Act: -0.0000

Data Index: 1583116 (Python Code)

Max Activating Token Index: 527

Text #17

Max Range: 1.8649. Min Range: -1.8649

Max Act: 1.2382. Min Act: -0.0000

Data Index: 1360533 (Python Code)

Max Activating Token Index: 976

Text #18

Max Range: 1.8649. Min Range: -1.8649

Max Act: 1.2647. Min Act: -0.0001

Data Index: 1383213 (Python Code)

Max Activating Token Index: 822

Text #19

Max Range: 1.8649. Min Range: -1.8649

Max Act: 1.2666. Min Act: -0.0001

Data Index: 1575227 (Python Code)

Max Activating Token Index: 706