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

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

Neuron 2729 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: 0.4752. Min Range: -0.4752

Max Act: 0.4752. Min Act: -0.0000

Data Index: 714898 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.4238. Min Act: -0.0000

Data Index: 1627902 (Python Code)

Max Activating Token Index: 880

Text #2

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.4161. Min Act: -0.0000

Data Index: 1433531 (Python Code)

Max Activating Token Index: 809

Text #3

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.4276. Min Act: -0.0000

Data Index: 1258808 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3913. Min Act: -0.0000

Data Index: 1467022 (Python Code)

Max Activating Token Index: 818

Text #5

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3859. Min Act: -0.0000

Data Index: 42688 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3751. Min Act: -0.0000

Data Index: 1373349 (Python Code)

Max Activating Token Index: 787

Text #7

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.4083. Min Act: -0.0000

Data Index: 1529402 (Python Code)

Max Activating Token Index: 909

Text #8

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.4387. Min Act: -0.0000

Data Index: 977631 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3426. Min Act: -0.0000

Data Index: 1030827 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3435. Min Act: -0.0000

Data Index: 789550 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3618. Min Act: -0.0000

Data Index: 498579 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3505. Min Act: -0.0000

Data Index: 921373 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3572. Min Act: -0.0000

Data Index: 994119 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1307508 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3703. Min Act: -0.0000

Data Index: 528933 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.2579. Min Act: -0.0000

Data Index: 341951 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3692. Min Act: -0.0000

Data Index: 165682 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3771. Min Act: -0.0000

Data Index: 1629345 (Python Code)

Max Activating Token Index: 629

Text #19

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3338. Min Act: -0.0000

Data Index: 312810 (C4 (Web Text))

Max Activating Token Index: 873