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

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

Neuron 4048 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3538. Min Range: -2.3538

Max Act: 2.3088. Min Act: -0.0001

Data Index: 1482181 (Python Code)

Max Activating Token Index: 727

Text #1

Max Range: 2.3538. Min Range: -2.3538

Max Act: 2.3538. Min Act: -0.0000

Data Index: 1594749 (Python Code)

Max Activating Token Index: 667

Text #2

Max Range: 2.3538. Min Range: -2.3538

Max Act: 2.1850. Min Act: -0.0001

Data Index: 1571563 (Python Code)

Max Activating Token Index: 45

Text #3

Max Range: 2.3538. Min Range: -2.3538

Max Act: 2.1294. Min Act: -0.0000

Data Index: 1496156 (Python Code)

Max Activating Token Index: 585

Text #4

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.9789. Min Act: -0.0001

Data Index: 1513112 (Python Code)

Max Activating Token Index: 257

Text #5

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.9533. Min Act: -0.0000

Data Index: 1529225 (Python Code)

Max Activating Token Index: 968

Text #6

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.8685. Min Act: -0.0001

Data Index: 1376078 (Python Code)

Max Activating Token Index: 776

Text #7

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.9331. Min Act: -0.0001

Data Index: 1595781 (Python Code)

Max Activating Token Index: 89

Text #8

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.7577. Min Act: -0.0001

Data Index: 1385710 (Python Code)

Max Activating Token Index: 802

Text #9

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.9653. Min Act: -0.0001

Data Index: 1632214 (Python Code)

Max Activating Token Index: 853

Text #10

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.9578. Min Act: -0.0001

Data Index: 1494742 (Python Code)

Max Activating Token Index: 121

Text #11

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.8557. Min Act: -0.0000

Data Index: 1364762 (Python Code)

Max Activating Token Index: 380

Text #12

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.8316. Min Act: -0.0001

Data Index: 1617928 (Python Code)

Max Activating Token Index: 546

Text #13

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.9181. Min Act: -0.0001

Data Index: 1461934 (Python Code)

Max Activating Token Index: 1005

Text #14

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.7587. Min Act: 0.0000

Data Index: 1628224 (Python Code)

Max Activating Token Index: 570

Text #15

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.7854. Min Act: -0.0001

Data Index: 1637629 (Python Code)

Max Activating Token Index: 701

Text #16

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.8826. Min Act: -0.0000

Data Index: 1480348 (Python Code)

Max Activating Token Index: 297

Text #17

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.7652. Min Act: -0.0001

Data Index: 1392841 (Python Code)

Max Activating Token Index: 333

Text #18

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.7016. Min Act: -0.0001

Data Index: 1448159 (Python Code)

Max Activating Token Index: 835

Text #19

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.7340. Min Act: -0.0000

Data Index: 1571599 (Python Code)

Max Activating Token Index: 543