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

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

Neuron 491 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1223. Min Act: -0.0001

Data Index: 1428991 (Python Code)

Max Activating Token Index: 443

Text #1

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1141. Min Act: -0.0001

Data Index: 1558913 (Python Code)

Max Activating Token Index: 359

Text #2

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1465377 (Python Code)

Max Activating Token Index: 141

Text #3

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1103. Min Act: -0.0001

Data Index: 1608057 (Python Code)

Max Activating Token Index: 1015

Text #4

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1155. Min Act: -0.0001

Data Index: 1391408 (Python Code)

Max Activating Token Index: 79

Text #5

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1204. Min Act: -0.0001

Data Index: 1635424 (Python Code)

Max Activating Token Index: 264

Text #6

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1193. Min Act: -0.0001

Data Index: 1423158 (Python Code)

Max Activating Token Index: 20

Text #7

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1394405 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1081. Min Act: -0.0001

Data Index: 1409420 (Python Code)

Max Activating Token Index: 196

Text #9

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1028. Min Act: -0.0001

Data Index: 1543338 (Python Code)

Max Activating Token Index: 57

Text #10

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0950. Min Act: -0.0001

Data Index: 1434314 (Python Code)

Max Activating Token Index: 131

Text #11

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1037. Min Act: -0.0001

Data Index: 1545893 (Python Code)

Max Activating Token Index: 577

Text #12

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0963. Min Act: -0.0001

Data Index: 1638954 (Python Code)

Max Activating Token Index: 977

Text #13

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1525485 (Python Code)

Max Activating Token Index: 11

Text #14

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0986. Min Act: -0.0001

Data Index: 1549441 (Python Code)

Max Activating Token Index: 35

Text #15

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1437229 (Python Code)

Max Activating Token Index: 1014

Text #16

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0900. Min Act: -0.0001

Data Index: 1592172 (Python Code)

Max Activating Token Index: 175

Text #17

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0964. Min Act: -0.0001

Data Index: 1483398 (Python Code)

Max Activating Token Index: 260

Text #18

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0819. Min Act: -0.0001

Data Index: 1463780 (Python Code)

Max Activating Token Index: 807

Text #19

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1572113 (Python Code)

Max Activating Token Index: 392