Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5592 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.6246. Min Range: -4.6246

Max Act: 4.6246. Min Act: -0.0000

Data Index: 521702 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 4.6246. Min Range: -4.6246

Max Act: 3.6793. Min Act: -0.0001

Data Index: 567816 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 4.6246. Min Range: -4.6246

Max Act: 3.7383. Min Act: -0.0000

Data Index: 532832 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 4.6246. Min Range: -4.6246

Max Act: 3.6573. Min Act: -0.0001

Data Index: 365476 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 4.6246. Min Range: -4.6246

Max Act: 3.3672. Min Act: -0.0001

Data Index: 1109661 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 4.6246. Min Range: -4.6246

Max Act: 3.5096. Min Act: -0.0000

Data Index: 834951 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 4.6246. Min Range: -4.6246

Max Act: 3.6853. Min Act: -0.0001

Data Index: 428473 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 4.6246. Min Range: -4.6246

Max Act: 3.8942. Min Act: -0.0000

Data Index: 168054 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 4.6246. Min Range: -4.6246

Max Act: 3.5450. Min Act: -0.0001

Data Index: 792524 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 4.6246. Min Range: -4.6246

Max Act: 3.5504. Min Act: -0.0000

Data Index: 1118010 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 4.6246. Min Range: -4.6246

Max Act: 3.5361. Min Act: -0.0001

Data Index: 235150 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 4.6246. Min Range: -4.6246

Max Act: 3.3604. Min Act: -0.0001

Data Index: 95935 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 4.6246. Min Range: -4.6246

Max Act: 3.5025. Min Act: -0.0000

Data Index: 906724 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 4.6246. Min Range: -4.6246

Max Act: 3.5995. Min Act: -0.0000

Data Index: 574690 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 4.6246. Min Range: -4.6246

Max Act: 3.2860. Min Act: -0.0001

Data Index: 204928 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 4.6246. Min Range: -4.6246

Max Act: 3.2869. Min Act: -0.0000

Data Index: 993002 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 4.6246. Min Range: -4.6246

Max Act: 3.4196. Min Act: -0.0000

Data Index: 1189243 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 4.6246. Min Range: -4.6246

Max Act: 3.2490. Min Act: -0.0001

Data Index: 207123 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 4.6246. Min Range: -4.6246

Max Act: 3.3841. Min Act: -0.0000

Data Index: 400002 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 4.6246. Min Range: -4.6246

Max Act: 3.2758. Min Act: -0.0000

Data Index: 368302 (C4 (Web Text))

Max Activating Token Index: 747