Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6038 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1523. Min Range: -2.1523

Max Act: 2.1523. Min Act: -0.0000

Data Index: 1566216 (Python Code)

Max Activating Token Index: 606

Text #1

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.8415. Min Act: -0.0000

Data Index: 1552448 (Python Code)

Max Activating Token Index: 409

Text #2

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.6629. Min Act: -0.0000

Data Index: 1498801 (Python Code)

Max Activating Token Index: 669

Text #3

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.5869. Min Act: -0.0000

Data Index: 222709 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.6750. Min Act: -0.0000

Data Index: 1647824 (Python Code)

Max Activating Token Index: 543

Text #5

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.5786. Min Act: -0.0000

Data Index: 1430613 (Python Code)

Max Activating Token Index: 267

Text #6

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.5261. Min Act: -0.0000

Data Index: 1580187 (Python Code)

Max Activating Token Index: 76

Text #7

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.4494. Min Act: -0.0000

Data Index: 1420895 (Python Code)

Max Activating Token Index: 714

Text #8

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.4019. Min Act: -0.0000

Data Index: 1040258 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.3814. Min Act: -0.0000

Data Index: 1617283 (Python Code)

Max Activating Token Index: 324

Text #10

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.3620. Min Act: -0.0000

Data Index: 1373396 (Python Code)

Max Activating Token Index: 1006

Text #11

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.4307. Min Act: -0.0000

Data Index: 1572279 (Python Code)

Max Activating Token Index: 840

Text #12

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.3607. Min Act: -0.0000

Data Index: 1405721 (Python Code)

Max Activating Token Index: 610

Text #13

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.3435. Min Act: -0.0000

Data Index: 1640347 (Python Code)

Max Activating Token Index: 877

Text #14

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.3458. Min Act: -0.0000

Data Index: 296946 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.4230. Min Act: -0.0000

Data Index: 1434697 (Python Code)

Max Activating Token Index: 503

Text #16

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.3472. Min Act: -0.0000

Data Index: 1451975 (Python Code)

Max Activating Token Index: 741

Text #17

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.3390. Min Act: -0.0000

Data Index: 1482578 (Python Code)

Max Activating Token Index: 878

Text #18

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.3227. Min Act: -0.0000

Data Index: 1570798 (Python Code)

Max Activating Token Index: 503

Text #19

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.3147. Min Act: -0.0000

Data Index: 1653716 (Python Code)

Max Activating Token Index: 649