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

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

Neuron 2127 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5791. Min Range: -1.5791

Max Act: 1.5791. Min Act: -0.0000

Data Index: 1520340 (Python Code)

Max Activating Token Index: 177

Text #1

Max Range: 1.5791. Min Range: -1.5791

Max Act: 1.3786. Min Act: -0.0000

Data Index: 1425541 (Python Code)

Max Activating Token Index: 168

Text #2

Max Range: 1.5791. Min Range: -1.5791

Max Act: 1.3322. Min Act: -0.0000

Data Index: 685522 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 1.5791. Min Range: -1.5791

Max Act: 1.3058. Min Act: -0.0000

Data Index: 1561328 (Python Code)

Max Activating Token Index: 130

Text #4

Max Range: 1.5791. Min Range: -1.5791

Max Act: 1.1178. Min Act: -0.0000

Data Index: 1162561 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 1.5791. Min Range: -1.5791

Max Act: 1.1475. Min Act: -0.0000

Data Index: 1535715 (Python Code)

Max Activating Token Index: 60

Text #6

Max Range: 1.5791. Min Range: -1.5791

Max Act: 1.1094. Min Act: -0.0000

Data Index: 927832 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 1.5791. Min Range: -1.5791

Max Act: 1.0398. Min Act: -0.0000

Data Index: 1645325 (Python Code)

Max Activating Token Index: 74

Text #8

Max Range: 1.5791. Min Range: -1.5791

Max Act: 1.0309. Min Act: -0.0000

Data Index: 1592096 (Python Code)

Max Activating Token Index: 47

Text #9

Max Range: 1.5791. Min Range: -1.5791

Max Act: 1.0259. Min Act: -0.0000

Data Index: 1572799 (Python Code)

Max Activating Token Index: 57

Text #10

Max Range: 1.5791. Min Range: -1.5791

Max Act: 1.0276. Min Act: -0.0000

Data Index: 91398 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 1.5791. Min Range: -1.5791

Max Act: 0.9467. Min Act: 0.0001

Data Index: 1394876 (Python Code)

Max Activating Token Index: 75

Text #12

Max Range: 1.5791. Min Range: -1.5791

Max Act: 1.0414. Min Act: -0.0000

Data Index: 681141 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 1.5791. Min Range: -1.5791

Max Act: 0.9389. Min Act: -0.0000

Data Index: 1389087 (Python Code)

Max Activating Token Index: 135

Text #14

Max Range: 1.5791. Min Range: -1.5791

Max Act: 0.9926. Min Act: -0.0000

Data Index: 1089210 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 1.5791. Min Range: -1.5791

Max Act: 0.9821. Min Act: -0.0000

Data Index: 1327925 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 1.5791. Min Range: -1.5791

Max Act: 0.9030. Min Act: -0.0000

Data Index: 1218801 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 1.5791. Min Range: -1.5791

Max Act: 0.9207. Min Act: -0.0000

Data Index: 1158894 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 1.5791. Min Range: -1.5791

Max Act: 0.9793. Min Act: -0.0000

Data Index: 1248238 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 1.5791. Min Range: -1.5791

Max Act: 0.8992. Min Act: -0.0000

Data Index: 371142 (C4 (Web Text))

Max Activating Token Index: 565