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

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

Neuron 3363 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0763. Min Range: -1.0763

Max Act: 1.0763. Min Act: -0.0001

Data Index: 1145613 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.8562. Min Act: -0.0000

Data Index: 122697 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.7794. Min Act: -0.0000

Data Index: 721187 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1109391 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.7439. Min Act: -0.0000

Data Index: 178741 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.7147. Min Act: -0.0000

Data Index: 1285973 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.7426. Min Act: -0.0000

Data Index: 500316 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1130031 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.5968. Min Act: -0.0000

Data Index: 358856 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1091666 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.5797. Min Act: -0.0000

Data Index: 1038809 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.5819. Min Act: -0.0000

Data Index: 564127 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.5751. Min Act: -0.0000

Data Index: 713348 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.5838. Min Act: -0.0000

Data Index: 844749 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.5417. Min Act: -0.0000

Data Index: 144689 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.5407. Min Act: -0.0000

Data Index: 515684 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.5361. Min Act: -0.0000

Data Index: 428865 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.5650. Min Act: -0.0000

Data Index: 495468 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.5621. Min Act: -0.0000

Data Index: 547500 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.5622. Min Act: -0.0000

Data Index: 502 (C4 (Web Text))

Max Activating Token Index: 919