Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2073 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.7423. Min Range: -2.7423

Max Act: 2.7423. Min Act: 0.0001

Data Index: 1172830 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 2.7423. Min Range: -2.7423

Max Act: 2.2797. Min Act: -0.0000

Data Index: 547015 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 2.7423. Min Range: -2.7423

Max Act: 2.1713. Min Act: -0.0000

Data Index: 466034 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 2.7423. Min Range: -2.7423

Max Act: 2.1350. Min Act: -0.0000

Data Index: 1357813 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 2.7423. Min Range: -2.7423

Max Act: 2.0023. Min Act: -0.0000

Data Index: 675955 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 2.7423. Min Range: -2.7423

Max Act: 1.9552. Min Act: -0.0000

Data Index: 147548 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 2.7423. Min Range: -2.7423

Max Act: 2.0268. Min Act: -0.0000

Data Index: 193810 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 2.7423. Min Range: -2.7423

Max Act: 1.9878. Min Act: -0.0000

Data Index: 1348004 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 2.7423. Min Range: -2.7423

Max Act: 1.8792. Min Act: -0.0000

Data Index: 701124 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 2.7423. Min Range: -2.7423

Max Act: 1.9526. Min Act: -0.0000

Data Index: 382861 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 2.7423. Min Range: -2.7423

Max Act: 2.0602. Min Act: -0.0000

Data Index: 183145 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 2.7423. Min Range: -2.7423

Max Act: 1.9454. Min Act: -0.0000

Data Index: 550298 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 2.7423. Min Range: -2.7423

Max Act: 2.0173. Min Act: -0.0000

Data Index: 114500 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 2.7423. Min Range: -2.7423

Max Act: 1.8932. Min Act: -0.0000

Data Index: 589523 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 2.7423. Min Range: -2.7423

Max Act: 1.7764. Min Act: -0.0000

Data Index: 477486 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 2.7423. Min Range: -2.7423

Max Act: 1.8477. Min Act: -0.0000

Data Index: 790340 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 2.7423. Min Range: -2.7423

Max Act: 1.8419. Min Act: 0.0000

Data Index: 1033799 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 2.7423. Min Range: -2.7423

Max Act: 1.8438. Min Act: -0.0000

Data Index: 16221 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 2.7423. Min Range: -2.7423

Max Act: 1.8091. Min Act: -0.0000

Data Index: 832644 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 2.7423. Min Range: -2.7423

Max Act: 1.8090. Min Act: -0.0000

Data Index: 1087953 (C4 (Web Text))

Max Activating Token Index: 128