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

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

Neuron 23 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1276. Min Act: -0.0001

Data Index: 1471313 (Python Code)

Max Activating Token Index: 448

Text #1

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1279. Min Act: -0.0001

Data Index: 54701 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1204. Min Act: -0.0001

Data Index: 1381890 (Python Code)

Max Activating Token Index: 128

Text #3

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1286. Min Act: -0.0001

Data Index: 935512 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1022. Min Act: -0.0001

Data Index: 1556333 (Python Code)

Max Activating Token Index: 606

Text #5

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1075861 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1186. Min Act: -0.0001

Data Index: 1063045 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1221. Min Act: -0.0001

Data Index: 464944 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1211. Min Act: -0.0001

Data Index: 1212071 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1209. Min Act: -0.0001

Data Index: 1647325 (Python Code)

Max Activating Token Index: 326

Text #10

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1129. Min Act: -0.0001

Data Index: 108887 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1084. Min Act: -0.0001

Data Index: 1369050 (Python Code)

Max Activating Token Index: 226

Text #12

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1159. Min Act: -0.0001

Data Index: 101177 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1109. Min Act: -0.0001

Data Index: 331535 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1128022 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1126. Min Act: -0.0001

Data Index: 293808 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1093. Min Act: -0.0001

Data Index: 1307553 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1062. Min Act: -0.0001

Data Index: 1312713 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1105. Min Act: -0.0001

Data Index: 462291 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1176. Min Act: -0.0001

Data Index: 152008 (C4 (Web Text))

Max Activating Token Index: 473