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

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

Neuron 2028 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1396. Min Act: -0.0002

Data Index: 1454871 (Python Code)

Max Activating Token Index: 372

Text #1

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1368. Min Act: -0.0002

Data Index: 271481 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1341. Min Act: -0.0002

Data Index: 286765 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1190. Min Act: -0.0002

Data Index: 482219 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1161. Min Act: -0.0002

Data Index: 1548767 (Python Code)

Max Activating Token Index: 40

Text #5

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1089. Min Act: -0.0002

Data Index: 483223 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1082. Min Act: -0.0002

Data Index: 1375693 (Python Code)

Max Activating Token Index: 235

Text #7

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1092. Min Act: -0.0002

Data Index: 171057 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1059. Min Act: -0.0002

Data Index: 137219 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1055. Min Act: -0.0002

Data Index: 1648474 (Python Code)

Max Activating Token Index: 178

Text #10

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1032. Min Act: -0.0002

Data Index: 190925 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1063. Min Act: -0.0002

Data Index: 1474333 (Python Code)

Max Activating Token Index: 28

Text #12

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1019. Min Act: -0.0002

Data Index: 611750 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1022. Min Act: -0.0002

Data Index: 821221 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1004. Min Act: -0.0002

Data Index: 60710 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.0992. Min Act: -0.0002

Data Index: 899742 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1000. Min Act: -0.0002

Data Index: 245476 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.0973. Min Act: -0.0002

Data Index: 1153467 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1029. Min Act: -0.0002

Data Index: 768794 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.0997. Min Act: -0.0002

Data Index: 374023 (C4 (Web Text))

Max Activating Token Index: 342