Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 268 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8860. Min Range: -2.8860

Max Act: 2.6277. Min Act: -0.0000

Data Index: 1617862 (Python Code)

Max Activating Token Index: 367

Text #1

Max Range: 2.8860. Min Range: -2.8860

Max Act: 2.6772. Min Act: -0.0000

Data Index: 1374541 (Python Code)

Max Activating Token Index: 773

Text #2

Max Range: 2.8860. Min Range: -2.8860

Max Act: 2.6608. Min Act: -0.0000

Data Index: 1639447 (Python Code)

Max Activating Token Index: 624

Text #3

Max Range: 2.8860. Min Range: -2.8860

Max Act: 2.8860. Min Act: -0.0000

Data Index: 1506900 (Python Code)

Max Activating Token Index: 655

Text #4

Max Range: 2.8860. Min Range: -2.8860

Max Act: 2.4636. Min Act: -0.0000

Data Index: 1482981 (Python Code)

Max Activating Token Index: 135

Text #5

Max Range: 2.8860. Min Range: -2.8860

Max Act: 2.4769. Min Act: -0.0000

Data Index: 1445950 (Python Code)

Max Activating Token Index: 691

Text #6

Max Range: 2.8860. Min Range: -2.8860

Max Act: 2.3202. Min Act: -0.0000

Data Index: 1516898 (Python Code)

Max Activating Token Index: 774

Text #7

Max Range: 2.8860. Min Range: -2.8860

Max Act: 2.5485. Min Act: -0.0000

Data Index: 1597273 (Python Code)

Max Activating Token Index: 507

Text #8

Max Range: 2.8860. Min Range: -2.8860

Max Act: 2.4845. Min Act: -0.0000

Data Index: 1597290 (Python Code)

Max Activating Token Index: 570

Text #9

Max Range: 2.8860. Min Range: -2.8860

Max Act: 2.3368. Min Act: -0.0000

Data Index: 1579102 (Python Code)

Max Activating Token Index: 221

Text #10

Max Range: 2.8860. Min Range: -2.8860

Max Act: 2.4142. Min Act: -0.0000

Data Index: 1360157 (Python Code)

Max Activating Token Index: 471

Text #11

Max Range: 2.8860. Min Range: -2.8860

Max Act: 2.3934. Min Act: -0.0000

Data Index: 1588303 (Python Code)

Max Activating Token Index: 382

Text #12

Max Range: 2.8860. Min Range: -2.8860

Max Act: 2.3834. Min Act: -0.0000

Data Index: 1635592 (Python Code)

Max Activating Token Index: 642

Text #13

Max Range: 2.8860. Min Range: -2.8860

Max Act: 2.3531. Min Act: -0.0000

Data Index: 1644165 (Python Code)

Max Activating Token Index: 306

Text #14

Max Range: 2.8860. Min Range: -2.8860

Max Act: 2.0764. Min Act: -0.0000

Data Index: 1653884 (Python Code)

Max Activating Token Index: 902

Text #15

Max Range: 2.8860. Min Range: -2.8860

Max Act: 2.3112. Min Act: -0.0000

Data Index: 1652956 (Python Code)

Max Activating Token Index: 659

Text #16

Max Range: 2.8860. Min Range: -2.8860

Max Act: 2.4328. Min Act: -0.0000

Data Index: 1448674 (Python Code)

Max Activating Token Index: 419

Text #17

Max Range: 2.8860. Min Range: -2.8860

Max Act: 2.2084. Min Act: -0.0000

Data Index: 1637265 (Python Code)

Max Activating Token Index: 789

Text #18

Max Range: 2.8860. Min Range: -2.8860

Max Act: 2.2085. Min Act: -0.0000

Data Index: 1508220 (Python Code)

Max Activating Token Index: 586

Text #19

Max Range: 2.8860. Min Range: -2.8860

Max Act: 2.2735. Min Act: -0.0000

Data Index: 1579940 (Python Code)

Max Activating Token Index: 510