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

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

Neuron 1939 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.3374. Min Act: -0.0000

Data Index: 942622 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.3157. Min Act: -0.0000

Data Index: 732500 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2900. Min Act: -0.0000

Data Index: 167402 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2925. Min Act: -0.0000

Data Index: 1090233 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2873. Min Act: -0.0000

Data Index: 667561 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2778. Min Act: -0.0000

Data Index: 533791 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2586. Min Act: -0.0000

Data Index: 293935 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2880. Min Act: -0.0000

Data Index: 1297589 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2710. Min Act: -0.0000

Data Index: 280030 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1295379 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2779. Min Act: -0.0000

Data Index: 1314432 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2656. Min Act: -0.0000

Data Index: 1202771 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2792. Min Act: -0.0000

Data Index: 834412 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2641. Min Act: -0.0000

Data Index: 281092 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2702. Min Act: -0.0000

Data Index: 79365 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2683. Min Act: -0.0000

Data Index: 813302 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1133553 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2639. Min Act: -0.0000

Data Index: 480948 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1048213 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2703. Min Act: -0.0000

Data Index: 881977 (C4 (Web Text))

Max Activating Token Index: 560