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

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

Neuron 1978 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.4524. Min Act: -0.0001

Data Index: 1182953 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3360. Min Act: -0.0001

Data Index: 960202 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3179. Min Act: -0.0001

Data Index: 6581 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3249. Min Act: -0.0001

Data Index: 645714 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2687. Min Act: -0.0001

Data Index: 693607 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2698. Min Act: -0.0001

Data Index: 1208197 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2682. Min Act: -0.0000

Data Index: 23421 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2653. Min Act: -0.0000

Data Index: 575086 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2706. Min Act: -0.0001

Data Index: 118772 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2647. Min Act: -0.0001

Data Index: 817957 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2566. Min Act: -0.0001

Data Index: 89729 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2424. Min Act: -0.0000

Data Index: 69582 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2692. Min Act: -0.0001

Data Index: 308875 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2573. Min Act: -0.0000

Data Index: 971486 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2576. Min Act: -0.0000

Data Index: 45852 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2374. Min Act: -0.0001

Data Index: 761828 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2546. Min Act: -0.0001

Data Index: 65636 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2445. Min Act: -0.0001

Data Index: 259103 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2525. Min Act: -0.0001

Data Index: 1280775 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2417. Min Act: -0.0001

Data Index: 860380 (C4 (Web Text))

Max Activating Token Index: 372