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

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

Neuron 1218 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.8959. Min Act: -0.0002

Data Index: 531232 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.9762. Min Act: -0.0002

Data Index: 1235384 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.9272. Min Act: -0.0002

Data Index: 543528 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.8639. Min Act: -0.0002

Data Index: 800313 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.9028. Min Act: -0.0002

Data Index: 841651 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.8159. Min Act: -0.0002

Data Index: 1198936 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.7577. Min Act: -0.0002

Data Index: 106456 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.7793. Min Act: -0.0002

Data Index: 726266 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.7039. Min Act: -0.0002

Data Index: 1078472 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.7730. Min Act: -0.0002

Data Index: 662736 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.7233. Min Act: -0.0002

Data Index: 1244820 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.7012. Min Act: -0.0002

Data Index: 743987 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.7862. Min Act: -0.0002

Data Index: 321112 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.8272. Min Act: -0.0002

Data Index: 492960 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.7160. Min Act: -0.0002

Data Index: 1250326 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.7276. Min Act: -0.0002

Data Index: 792093 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.7431. Min Act: -0.0002

Data Index: 1188992 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.7553. Min Act: -0.0002

Data Index: 120577 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.6894. Min Act: -0.0002

Data Index: 869287 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 0.9762. Min Range: -0.9762

Max Act: 0.7025. Min Act: -0.0002

Data Index: 596758 (C4 (Web Text))

Max Activating Token Index: 727