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

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

Neuron 1217 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0688. Min Range: -1.0688

Max Act: 1.0688. Min Act: -0.0000

Data Index: 1487168 (Python Code)

Max Activating Token Index: 971

Text #1

Max Range: 1.0688. Min Range: -1.0688

Max Act: 1.0138. Min Act: -0.0000

Data Index: 227429 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.9415. Min Act: -0.0000

Data Index: 1507402 (Python Code)

Max Activating Token Index: 926

Text #3

Max Range: 1.0688. Min Range: -1.0688

Max Act: 1.0004. Min Act: -0.0000

Data Index: 1098079 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8802. Min Act: -0.0000

Data Index: 1110238 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8894. Min Act: -0.0000

Data Index: 332030 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8245. Min Act: -0.0000

Data Index: 1468302 (Python Code)

Max Activating Token Index: 45

Text #7

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8396. Min Act: -0.0000

Data Index: 314332 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8772. Min Act: -0.0000

Data Index: 108629 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8123. Min Act: -0.0000

Data Index: 793209 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.7825. Min Act: -0.0000

Data Index: 167746 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8039. Min Act: -0.0000

Data Index: 1391305 (Python Code)

Max Activating Token Index: 70

Text #12

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8242. Min Act: -0.0000

Data Index: 1329702 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.7683. Min Act: -0.0000

Data Index: 1257367 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8135. Min Act: -0.0000

Data Index: 530626 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1399130 (Python Code)

Max Activating Token Index: 249

Text #16

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.7385. Min Act: -0.0000

Data Index: 1409562 (Python Code)

Max Activating Token Index: 192

Text #17

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1408832 (Python Code)

Max Activating Token Index: 979

Text #18

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.7522. Min Act: -0.0000

Data Index: 75061 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8196. Min Act: -0.0000

Data Index: 1360609 (Python Code)

Max Activating Token Index: 746