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

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

Neuron 3662 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: 2.3440. Min Range: -2.3440

Max Act: 2.3440. Min Act: -0.0000

Data Index: 1553589 (Python Code)

Max Activating Token Index: 75

Text #1

Max Range: 2.3440. Min Range: -2.3440

Max Act: 1.8557. Min Act: -0.0000

Data Index: 1499520 (Python Code)

Max Activating Token Index: 127

Text #2

Max Range: 2.3440. Min Range: -2.3440

Max Act: 1.7783. Min Act: -0.0000

Data Index: 1573551 (Python Code)

Max Activating Token Index: 741

Text #3

Max Range: 2.3440. Min Range: -2.3440

Max Act: 1.7559. Min Act: -0.0000

Data Index: 1526607 (Python Code)

Max Activating Token Index: 75

Text #4

Max Range: 2.3440. Min Range: -2.3440

Max Act: 1.5689. Min Act: -0.0000

Data Index: 1585620 (Python Code)

Max Activating Token Index: 109

Text #5

Max Range: 2.3440. Min Range: -2.3440

Max Act: 1.5111. Min Act: -0.0000

Data Index: 1585314 (Python Code)

Max Activating Token Index: 252

Text #6

Max Range: 2.3440. Min Range: -2.3440

Max Act: 1.5009. Min Act: -0.0000

Data Index: 1530421 (Python Code)

Max Activating Token Index: 312

Text #7

Max Range: 2.3440. Min Range: -2.3440

Max Act: 1.5570. Min Act: -0.0000

Data Index: 1383169 (Python Code)

Max Activating Token Index: 374

Text #8

Max Range: 2.3440. Min Range: -2.3440

Max Act: 1.3732. Min Act: -0.0000

Data Index: 1545399 (Python Code)

Max Activating Token Index: 208

Text #9

Max Range: 2.3440. Min Range: -2.3440

Max Act: 1.3655. Min Act: -0.0000

Data Index: 1441084 (Python Code)

Max Activating Token Index: 294

Text #10

Max Range: 2.3440. Min Range: -2.3440

Max Act: 1.1813. Min Act: -0.0000

Data Index: 1445713 (Python Code)

Max Activating Token Index: 455

Text #11

Max Range: 2.3440. Min Range: -2.3440

Max Act: 1.2619. Min Act: -0.0000

Data Index: 1442794 (Python Code)

Max Activating Token Index: 117

Text #12

Max Range: 2.3440. Min Range: -2.3440

Max Act: 1.3828. Min Act: -0.0000

Data Index: 1403182 (Python Code)

Max Activating Token Index: 107

Text #13

Max Range: 2.3440. Min Range: -2.3440

Max Act: 1.3284. Min Act: -0.0000

Data Index: 1407802 (Python Code)

Max Activating Token Index: 823

Text #14

Max Range: 2.3440. Min Range: -2.3440

Max Act: 1.2070. Min Act: -0.0000

Data Index: 1422436 (Python Code)

Max Activating Token Index: 95

Text #15

Max Range: 2.3440. Min Range: -2.3440

Max Act: 1.2649. Min Act: -0.0000

Data Index: 1598513 (Python Code)

Max Activating Token Index: 84

Text #16

Max Range: 2.3440. Min Range: -2.3440

Max Act: 1.1908. Min Act: -0.0000

Data Index: 1427715 (Python Code)

Max Activating Token Index: 257

Text #17

Max Range: 2.3440. Min Range: -2.3440

Max Act: 1.3166. Min Act: -0.0000

Data Index: 1617684 (Python Code)

Max Activating Token Index: 136

Text #18

Max Range: 2.3440. Min Range: -2.3440

Max Act: 1.2129. Min Act: -0.0000

Data Index: 1497946 (Python Code)

Max Activating Token Index: 131

Text #19

Max Range: 2.3440. Min Range: -2.3440

Max Act: 1.1691. Min Act: -0.0000

Data Index: 1633678 (Python Code)

Max Activating Token Index: 86