Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3762 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.5531. Min Act: -0.0000

Data Index: 26292 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.5111. Min Act: -0.0000

Data Index: 907683 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4499. Min Act: -0.0000

Data Index: 863013 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3733. Min Act: -0.0000

Data Index: 773497 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3437. Min Act: -0.0000

Data Index: 429237 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3624. Min Act: -0.0000

Data Index: 513105 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3662. Min Act: -0.0000

Data Index: 50919 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3276. Min Act: -0.0000

Data Index: 467843 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1152574 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3145. Min Act: -0.0000

Data Index: 76464 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3418. Min Act: -0.0000

Data Index: 1089899 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3348. Min Act: -0.0000

Data Index: 501268 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3396. Min Act: -0.0000

Data Index: 999600 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3216. Min Act: -0.0000

Data Index: 618467 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3108. Min Act: -0.0000

Data Index: 776363 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3208. Min Act: -0.0000

Data Index: 226887 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3083. Min Act: -0.0000

Data Index: 811125 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3131. Min Act: -0.0000

Data Index: 364660 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3152. Min Act: -0.0000

Data Index: 586742 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3215. Min Act: -0.0000

Data Index: 1274906 (C4 (Web Text))

Max Activating Token Index: 962