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

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

Neuron 5098 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0980. Min Range: -6.0980

Max Act: 6.0980. Min Act: -0.0000

Data Index: 737126 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 6.0980. Min Range: -6.0980

Max Act: 4.8342. Min Act: -0.0000

Data Index: 92278 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 6.0980. Min Range: -6.0980

Max Act: 4.8012. Min Act: -0.0000

Data Index: 1043091 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 6.0980. Min Range: -6.0980

Max Act: 4.4176. Min Act: -0.0000

Data Index: 1322181 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 6.0980. Min Range: -6.0980

Max Act: 4.3115. Min Act: -0.0000

Data Index: 993550 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 6.0980. Min Range: -6.0980

Max Act: 4.2977. Min Act: -0.0000

Data Index: 59130 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 6.0980. Min Range: -6.0980

Max Act: 4.4532. Min Act: -0.0000

Data Index: 1019464 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 6.0980. Min Range: -6.0980

Max Act: 4.6163. Min Act: -0.0000

Data Index: 1113479 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 6.0980. Min Range: -6.0980

Max Act: 4.6005. Min Act: -0.0000

Data Index: 439900 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 6.0980. Min Range: -6.0980

Max Act: 4.1195. Min Act: -0.0000

Data Index: 1027476 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 6.0980. Min Range: -6.0980

Max Act: 4.4067. Min Act: -0.0000

Data Index: 528306 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 6.0980. Min Range: -6.0980

Max Act: 4.4150. Min Act: -0.0000

Data Index: 880602 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 6.0980. Min Range: -6.0980

Max Act: 4.4268. Min Act: -0.0000

Data Index: 340303 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 6.0980. Min Range: -6.0980

Max Act: 4.1195. Min Act: -0.0000

Data Index: 887873 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 6.0980. Min Range: -6.0980

Max Act: 4.3438. Min Act: -0.0000

Data Index: 526477 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 6.0980. Min Range: -6.0980

Max Act: 4.3237. Min Act: -0.0000

Data Index: 733466 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 6.0980. Min Range: -6.0980

Max Act: 4.3065. Min Act: -0.0000

Data Index: 511103 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 6.0980. Min Range: -6.0980

Max Act: 4.2781. Min Act: -0.0000

Data Index: 583812 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 6.0980. Min Range: -6.0980

Max Act: 4.1224. Min Act: -0.0000

Data Index: 561238 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 6.0980. Min Range: -6.0980

Max Act: 4.2730. Min Act: -0.0000

Data Index: 904583 (C4 (Web Text))

Max Activating Token Index: 146