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

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

Neuron 1818 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: 3.7405. Min Range: -3.7405

Max Act: 3.7405. Min Act: -0.0000

Data Index: 1370399 (Python Code)

Max Activating Token Index: 841

Text #1

Max Range: 3.7405. Min Range: -3.7405

Max Act: 3.5008. Min Act: -0.0000

Data Index: 1573417 (Python Code)

Max Activating Token Index: 16

Text #2

Max Range: 3.7405. Min Range: -3.7405

Max Act: 3.4601. Min Act: -0.0000

Data Index: 1533479 (Python Code)

Max Activating Token Index: 11

Text #3

Max Range: 3.7405. Min Range: -3.7405

Max Act: 3.6112. Min Act: -0.0000

Data Index: 1570944 (Python Code)

Max Activating Token Index: 700

Text #4

Max Range: 3.7405. Min Range: -3.7405

Max Act: 3.4455. Min Act: -0.0000

Data Index: 1422487 (Python Code)

Max Activating Token Index: 70

Text #5

Max Range: 3.7405. Min Range: -3.7405

Max Act: 3.4281. Min Act: -0.0000

Data Index: 1394224 (Python Code)

Max Activating Token Index: 291

Text #6

Max Range: 3.7405. Min Range: -3.7405

Max Act: 3.4997. Min Act: -0.0000

Data Index: 1566626 (Python Code)

Max Activating Token Index: 741

Text #7

Max Range: 3.7405. Min Range: -3.7405

Max Act: 2.9556. Min Act: -0.0000

Data Index: 1645806 (Python Code)

Max Activating Token Index: 276

Text #8

Max Range: 3.7405. Min Range: -3.7405

Max Act: 3.1491. Min Act: -0.0000

Data Index: 1655351 (Python Code)

Max Activating Token Index: 549

Text #9

Max Range: 3.7405. Min Range: -3.7405

Max Act: 3.0055. Min Act: -0.0001

Data Index: 1580104 (Python Code)

Max Activating Token Index: 311

Text #10

Max Range: 3.7405. Min Range: -3.7405

Max Act: 3.1350. Min Act: -0.0001

Data Index: 1522484 (Python Code)

Max Activating Token Index: 588

Text #11

Max Range: 3.7405. Min Range: -3.7405

Max Act: 2.9845. Min Act: -0.0000

Data Index: 1529410 (Python Code)

Max Activating Token Index: 651

Text #12

Max Range: 3.7405. Min Range: -3.7405

Max Act: 2.9695. Min Act: -0.0000

Data Index: 1382544 (Python Code)

Max Activating Token Index: 160

Text #13

Max Range: 3.7405. Min Range: -3.7405

Max Act: 3.1254. Min Act: -0.0001

Data Index: 1390284 (Python Code)

Max Activating Token Index: 399

Text #14

Max Range: 3.7405. Min Range: -3.7405

Max Act: 3.0891. Min Act: -0.0000

Data Index: 1479068 (Python Code)

Max Activating Token Index: 440

Text #15

Max Range: 3.7405. Min Range: -3.7405

Max Act: 2.8703. Min Act: -0.0000

Data Index: 1428944 (Python Code)

Max Activating Token Index: 562

Text #16

Max Range: 3.7405. Min Range: -3.7405

Max Act: 2.9705. Min Act: -0.0000

Data Index: 1561069 (Python Code)

Max Activating Token Index: 799

Text #17

Max Range: 3.7405. Min Range: -3.7405

Max Act: 2.7414. Min Act: -0.0000

Data Index: 1501459 (Python Code)

Max Activating Token Index: 955

Text #18

Max Range: 3.7405. Min Range: -3.7405

Max Act: 2.8867. Min Act: -0.0000

Data Index: 1428972 (Python Code)

Max Activating Token Index: 18

Text #19

Max Range: 3.7405. Min Range: -3.7405

Max Act: 2.8899. Min Act: -0.0000

Data Index: 1426421 (Python Code)

Max Activating Token Index: 519