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

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

Neuron 1637 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8105. Min Range: -2.8105

Max Act: 2.8105. Min Act: -0.0000

Data Index: 1638555 (Python Code)

Max Activating Token Index: 514

Text #1

Max Range: 2.8105. Min Range: -2.8105

Max Act: 2.6122. Min Act: -0.0000

Data Index: 1558402 (Python Code)

Max Activating Token Index: 120

Text #2

Max Range: 2.8105. Min Range: -2.8105

Max Act: 2.7571. Min Act: -0.0000

Data Index: 1633206 (Python Code)

Max Activating Token Index: 646

Text #3

Max Range: 2.8105. Min Range: -2.8105

Max Act: 2.6941. Min Act: -0.0000

Data Index: 1637625 (Python Code)

Max Activating Token Index: 663

Text #4

Max Range: 2.8105. Min Range: -2.8105

Max Act: 2.5129. Min Act: -0.0000

Data Index: 1470159 (Python Code)

Max Activating Token Index: 953

Text #5

Max Range: 2.8105. Min Range: -2.8105

Max Act: 2.6313. Min Act: -0.0000

Data Index: 1301016 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 2.8105. Min Range: -2.8105

Max Act: 2.5644. Min Act: -0.0000

Data Index: 1513543 (Python Code)

Max Activating Token Index: 96

Text #7

Max Range: 2.8105. Min Range: -2.8105

Max Act: 2.6648. Min Act: -0.0000

Data Index: 1648633 (Python Code)

Max Activating Token Index: 552

Text #8

Max Range: 2.8105. Min Range: -2.8105

Max Act: 2.4480. Min Act: -0.0000

Data Index: 568782 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 2.8105. Min Range: -2.8105

Max Act: 2.4100. Min Act: -0.0000

Data Index: 1612397 (Python Code)

Max Activating Token Index: 127

Text #10

Max Range: 2.8105. Min Range: -2.8105

Max Act: 2.5251. Min Act: -0.0000

Data Index: 1394829 (Python Code)

Max Activating Token Index: 631

Text #11

Max Range: 2.8105. Min Range: -2.8105

Max Act: 2.3579. Min Act: -0.0000

Data Index: 1477447 (Python Code)

Max Activating Token Index: 814

Text #12

Max Range: 2.8105. Min Range: -2.8105

Max Act: 2.3571. Min Act: -0.0000

Data Index: 1590019 (Python Code)

Max Activating Token Index: 261

Text #13

Max Range: 2.8105. Min Range: -2.8105

Max Act: 2.2776. Min Act: -0.0000

Data Index: 678971 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 2.8105. Min Range: -2.8105

Max Act: 2.2686. Min Act: -0.0000

Data Index: 1508048 (Python Code)

Max Activating Token Index: 39

Text #15

Max Range: 2.8105. Min Range: -2.8105

Max Act: 2.2684. Min Act: -0.0000

Data Index: 1431241 (Python Code)

Max Activating Token Index: 629

Text #16

Max Range: 2.8105. Min Range: -2.8105

Max Act: 2.2553. Min Act: -0.0000

Data Index: 1549312 (Python Code)

Max Activating Token Index: 562

Text #17

Max Range: 2.8105. Min Range: -2.8105

Max Act: 2.2488. Min Act: -0.0000

Data Index: 1634010 (Python Code)

Max Activating Token Index: 215

Text #18

Max Range: 2.8105. Min Range: -2.8105

Max Act: 2.2339. Min Act: -0.0000

Data Index: 1577843 (Python Code)

Max Activating Token Index: 529

Text #19

Max Range: 2.8105. Min Range: -2.8105

Max Act: 2.0840. Min Act: -0.0000

Data Index: 1603998 (Python Code)

Max Activating Token Index: 839