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

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

Neuron 1684 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1566. Min Range: -1.1566

Max Act: 1.1566. Min Act: -0.0001

Data Index: 1370573 (Python Code)

Max Activating Token Index: 294

Text #1

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.9934. Min Act: -0.0001

Data Index: 731386 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 1.1566. Min Range: -1.1566

Max Act: 1.0967. Min Act: -0.0001

Data Index: 1649726 (Python Code)

Max Activating Token Index: 158

Text #3

Max Range: 1.1566. Min Range: -1.1566

Max Act: 1.0253. Min Act: -0.0001

Data Index: 855172 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 1.1566. Min Range: -1.1566

Max Act: 1.0223. Min Act: -0.0001

Data Index: 1485267 (Python Code)

Max Activating Token Index: 131

Text #5

Max Range: 1.1566. Min Range: -1.1566

Max Act: 1.0081. Min Act: -0.0001

Data Index: 1525911 (Python Code)

Max Activating Token Index: 620

Text #6

Max Range: 1.1566. Min Range: -1.1566

Max Act: 1.0338. Min Act: -0.0001

Data Index: 1612572 (Python Code)

Max Activating Token Index: 130

Text #7

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.9186. Min Act: -0.0001

Data Index: 1479074 (Python Code)

Max Activating Token Index: 166

Text #8

Max Range: 1.1566. Min Range: -1.1566

Max Act: 1.0054. Min Act: -0.0001

Data Index: 1365730 (Python Code)

Max Activating Token Index: 86

Text #9

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.9673. Min Act: -0.0001

Data Index: 1363279 (Python Code)

Max Activating Token Index: 804

Text #10

Max Range: 1.1566. Min Range: -1.1566

Max Act: 1.0418. Min Act: -0.0001

Data Index: 1589112 (Python Code)

Max Activating Token Index: 920

Text #11

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.7637. Min Act: -0.0001

Data Index: 1097364 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8979. Min Act: -0.0001

Data Index: 1527413 (Python Code)

Max Activating Token Index: 686

Text #13

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.9517. Min Act: -0.0001

Data Index: 1438427 (Python Code)

Max Activating Token Index: 56

Text #14

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8688. Min Act: -0.0001

Data Index: 1382844 (Python Code)

Max Activating Token Index: 905

Text #15

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8955. Min Act: -0.0001

Data Index: 1483370 (Python Code)

Max Activating Token Index: 730

Text #16

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.9008. Min Act: -0.0001

Data Index: 1445690 (Python Code)

Max Activating Token Index: 82

Text #17

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8786. Min Act: -0.0001

Data Index: 1391996 (Python Code)

Max Activating Token Index: 741

Text #18

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8043. Min Act: -0.0001

Data Index: 916158 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8598. Min Act: -0.0001

Data Index: 586906 (C4 (Web Text))

Max Activating Token Index: 526