Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 494 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.7632. Min Act: -0.0001

Data Index: 439470 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.7177. Min Act: -0.0001

Data Index: 966749 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.7079. Min Act: -0.0001

Data Index: 619451 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6980. Min Act: -0.0001

Data Index: 266340 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6971. Min Act: -0.0001

Data Index: 354191 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.7148. Min Act: -0.0001

Data Index: 369732 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.7328. Min Act: -0.0001

Data Index: 742379 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6759. Min Act: -0.0001

Data Index: 577234 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6525. Min Act: -0.0001

Data Index: 408585 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6759. Min Act: -0.0001

Data Index: 1284357 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6948. Min Act: -0.0001

Data Index: 450983 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6935. Min Act: -0.0001

Data Index: 379028 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6946. Min Act: -0.0001

Data Index: 572782 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.7063. Min Act: -0.0001

Data Index: 523978 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6737. Min Act: -0.0001

Data Index: 922965 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6372. Min Act: -0.0001

Data Index: 435679 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6644. Min Act: -0.0001

Data Index: 1077142 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6170. Min Act: -0.0001

Data Index: 868022 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6595. Min Act: -0.0001

Data Index: 551200 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.7632. Min Range: -0.7632

Max Act: 0.6511. Min Act: -0.0001

Data Index: 1032877 (C4 (Web Text))

Max Activating Token Index: 846