Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4649 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.4196. Min Act: -0.0000

Data Index: 481716 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1031609 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.2956. Min Act: -0.0000

Data Index: 1489861 (Python Code)

Max Activating Token Index: 942

Text #3

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1116580 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3133. Min Act: -0.0000

Data Index: 359923 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.2906. Min Act: -0.0000

Data Index: 299218 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.2810. Min Act: -0.0000

Data Index: 1366766 (Python Code)

Max Activating Token Index: 433

Text #7

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.2647. Min Act: 0.0000

Data Index: 683055 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.2678. Min Act: -0.0000

Data Index: 170777 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.2415. Min Act: -0.0000

Data Index: 573985 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.2361. Min Act: -0.0000

Data Index: 1139364 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.2536. Min Act: -0.0000

Data Index: 243806 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.2444. Min Act: -0.0000

Data Index: 497293 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.2204. Min Act: -0.0000

Data Index: 251477 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.2071. Min Act: -0.0000

Data Index: 805870 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.2044. Min Act: -0.0000

Data Index: 881712 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.2080. Min Act: -0.0000

Data Index: 987275 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.2138. Min Act: -0.0000

Data Index: 652115 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.1921. Min Act: -0.0000

Data Index: 1577492 (Python Code)

Max Activating Token Index: 262

Text #19

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.2063. Min Act: -0.0000

Data Index: 526291 (C4 (Web Text))

Max Activating Token Index: 238