Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 642 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0640. Min Act: -0.0006

Data Index: 51791 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0628. Min Act: -0.0006

Data Index: 936616 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0541. Min Act: -0.0006

Data Index: 776191 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0512. Min Act: -0.0006

Data Index: 11103 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0475. Min Act: -0.0006

Data Index: 463702 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0569. Min Act: -0.0006

Data Index: 239871 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0551. Min Act: -0.0006

Data Index: 6484 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0476. Min Act: -0.0006

Data Index: 737367 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0481. Min Act: -0.0006

Data Index: 770807 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0525. Min Act: -0.0006

Data Index: 1123001 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0534. Min Act: -0.0006

Data Index: 1295740 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0493. Min Act: -0.0006

Data Index: 1264185 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0469. Min Act: -0.0006

Data Index: 234136 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0546. Min Act: -0.0006

Data Index: 742696 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0467. Min Act: -0.0006

Data Index: 872489 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0502. Min Act: -0.0006

Data Index: 308987 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0490. Min Act: -0.0006

Data Index: 482016 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0519. Min Act: -0.0006

Data Index: 738273 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0460. Min Act: -0.0006

Data Index: 1003656 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0519. Min Act: -0.0006

Data Index: 925251 (C4 (Web Text))

Max Activating Token Index: 314