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

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

Neuron 2959 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: 0.1402. Min Range: -0.1402

Max Act: 0.1402. Min Act: -0.0001

Data Index: 105974 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1366. Min Act: -0.0001

Data Index: 905308 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1307. Min Act: -0.0001

Data Index: 1217321 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1208. Min Act: -0.0001

Data Index: 749149 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1187. Min Act: -0.0001

Data Index: 981542 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1221. Min Act: -0.0001

Data Index: 301389 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1137. Min Act: -0.0001

Data Index: 610288 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.0950. Min Act: -0.0001

Data Index: 158227 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1112. Min Act: -0.0001

Data Index: 235721 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.0998. Min Act: -0.0001

Data Index: 265516 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1017. Min Act: -0.0001

Data Index: 763463 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1018. Min Act: -0.0001

Data Index: 294281 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1004. Min Act: -0.0001

Data Index: 1022573 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1043. Min Act: -0.0001

Data Index: 851925 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1041. Min Act: -0.0001

Data Index: 218831 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1068. Min Act: -0.0001

Data Index: 1294431 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1002. Min Act: -0.0001

Data Index: 1153444 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1079. Min Act: -0.0001

Data Index: 35835 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.0995. Min Act: -0.0001

Data Index: 1522052 (Python Code)

Max Activating Token Index: 247

Text #19

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.0952. Min Act: -0.0001

Data Index: 1036745 (C4 (Web Text))

Max Activating Token Index: 337