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

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

Neuron 1184 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: 0.0713. Min Range: -0.0713

Max Act: 0.0713. Min Act: -0.0006

Data Index: 1136795 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0601. Min Act: -0.0006

Data Index: 737071 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0560. Min Act: -0.0006

Data Index: 1094701 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0580. Min Act: -0.0006

Data Index: 1009923 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0508. Min Act: -0.0006

Data Index: 791327 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0582. Min Act: -0.0006

Data Index: 1147498 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0522. Min Act: -0.0006

Data Index: 293387 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0530. Min Act: -0.0006

Data Index: 195004 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0541. Min Act: -0.0006

Data Index: 1076805 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0538. Min Act: -0.0006

Data Index: 132228 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0493. Min Act: -0.0006

Data Index: 43198 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0443. Min Act: -0.0006

Data Index: 932235 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0511. Min Act: -0.0006

Data Index: 384658 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0484. Min Act: -0.0006

Data Index: 1262560 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0440. Min Act: -0.0006

Data Index: 1118098 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0485. Min Act: -0.0006

Data Index: 1356611 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0484. Min Act: -0.0006

Data Index: 442879 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0464. Min Act: -0.0006

Data Index: 956788 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0452. Min Act: -0.0006

Data Index: 558884 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0424. Min Act: -0.0006

Data Index: 286215 (C4 (Web Text))

Max Activating Token Index: 284