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

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

Neuron 3873 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4572. Min Act: -0.0001

Data Index: 1447707 (Python Code)

Max Activating Token Index: 184

Text #1

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4409. Min Act: -0.0001

Data Index: 1468962 (Python Code)

Max Activating Token Index: 136

Text #2

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4558. Min Act: -0.0001

Data Index: 1371818 (Python Code)

Max Activating Token Index: 308

Text #3

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4561. Min Act: -0.0001

Data Index: 1558436 (Python Code)

Max Activating Token Index: 328

Text #4

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4128. Min Act: -0.0001

Data Index: 1473525 (Python Code)

Max Activating Token Index: 90

Text #5

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4453. Min Act: -0.0001

Data Index: 1601180 (Python Code)

Max Activating Token Index: 348

Text #6

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4397. Min Act: -0.0001

Data Index: 1582937 (Python Code)

Max Activating Token Index: 42

Text #7

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4119. Min Act: -0.0001

Data Index: 1436809 (Python Code)

Max Activating Token Index: 65

Text #8

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4205. Min Act: -0.0001

Data Index: 1485579 (Python Code)

Max Activating Token Index: 321

Text #9

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3994. Min Act: -0.0001

Data Index: 1323529 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4128. Min Act: -0.0001

Data Index: 1397670 (Python Code)

Max Activating Token Index: 37

Text #11

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3975. Min Act: -0.0001

Data Index: 1417112 (Python Code)

Max Activating Token Index: 510

Text #12

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4091. Min Act: -0.0001

Data Index: 1429512 (Python Code)

Max Activating Token Index: 116

Text #13

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4101. Min Act: -0.0001

Data Index: 1576687 (Python Code)

Max Activating Token Index: 38

Text #14

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3852. Min Act: -0.0001

Data Index: 1526662 (Python Code)

Max Activating Token Index: 43

Text #15

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3735. Min Act: -0.0001

Data Index: 1407926 (Python Code)

Max Activating Token Index: 70

Text #16

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3822. Min Act: -0.0001

Data Index: 1550509 (Python Code)

Max Activating Token Index: 41

Text #17

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3788. Min Act: -0.0001

Data Index: 1579538 (Python Code)

Max Activating Token Index: 115

Text #18

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3807. Min Act: -0.0001

Data Index: 1611925 (Python Code)

Max Activating Token Index: 55

Text #19

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3945. Min Act: -0.0001

Data Index: 1584720 (Python Code)

Max Activating Token Index: 269