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

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

Neuron 2178 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1776. Min Act: -0.0001

Data Index: 1436434 (Python Code)

Max Activating Token Index: 361

Text #1

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1250. Min Act: -0.0001

Data Index: 734074 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1466. Min Act: -0.0001

Data Index: 1152476 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.2048. Min Act: -0.0001

Data Index: 1583428 (Python Code)

Max Activating Token Index: 757

Text #4

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1513. Min Act: -0.0001

Data Index: 793120 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1368. Min Act: -0.0001

Data Index: 318113 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1228. Min Act: -0.0001

Data Index: 406221 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1561. Min Act: -0.0001

Data Index: 1194437 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1195. Min Act: -0.0001

Data Index: 466178 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1163. Min Act: -0.0001

Data Index: 638899 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1176. Min Act: -0.0001

Data Index: 777261 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1128. Min Act: -0.0001

Data Index: 1308910 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1280. Min Act: -0.0001

Data Index: 470240 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1298. Min Act: -0.0001

Data Index: 1197014 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1080. Min Act: -0.0001

Data Index: 1027787 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1145397 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1133. Min Act: -0.0001

Data Index: 1406627 (Python Code)

Max Activating Token Index: 38

Text #17

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.0964. Min Act: -0.0001

Data Index: 1641994 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1013. Min Act: -0.0001

Data Index: 495362 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1114. Min Act: -0.0001

Data Index: 741951 (C4 (Web Text))

Max Activating Token Index: 118