Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1352 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.2385. Min Act: -0.0001

Data Index: 815663 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.2417. Min Act: -0.0001

Data Index: 204248 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.2225. Min Act: -0.0001

Data Index: 866279 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.2325. Min Act: -0.0001

Data Index: 373927 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.2229. Min Act: -0.0001

Data Index: 159311 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.2119. Min Act: -0.0000

Data Index: 1092724 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.2129. Min Act: -0.0001

Data Index: 949797 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.2094. Min Act: -0.0001

Data Index: 142168 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.2088. Min Act: -0.0001

Data Index: 884757 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.2090. Min Act: -0.0001

Data Index: 1463923 (Python Code)

Max Activating Token Index: 100

Text #10

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.2104. Min Act: -0.0001

Data Index: 1385953 (Python Code)

Max Activating Token Index: 445

Text #11

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.2030. Min Act: -0.0001

Data Index: 802649 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.2041. Min Act: -0.0001

Data Index: 1371292 (Python Code)

Max Activating Token Index: 308

Text #13

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.1945. Min Act: -0.0001

Data Index: 1593238 (Python Code)

Max Activating Token Index: 29

Text #14

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.1926. Min Act: -0.0001

Data Index: 865168 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.1906. Min Act: -0.0001

Data Index: 54867 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.2046. Min Act: -0.0001

Data Index: 1001491 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.1907. Min Act: -0.0001

Data Index: 1349538 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.1912. Min Act: -0.0001

Data Index: 391300 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.2417. Min Range: -0.2417

Max Act: 0.1904. Min Act: -0.0001

Data Index: 1541674 (Python Code)

Max Activating Token Index: 783