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

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

Neuron 2682 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.3788. Min Act: -0.0001

Data Index: 818042 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.1838. Min Act: -0.0001

Data Index: 1137640 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.2099. Min Act: -0.0001

Data Index: 359397 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.1096. Min Act: -0.0001

Data Index: 1122732 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.0715. Min Act: -0.0001

Data Index: 227376 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.0766. Min Act: -0.0001

Data Index: 217874 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.0645. Min Act: -0.0001

Data Index: 1024398 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.0216. Min Act: -0.0001

Data Index: 1336150 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 1.3788. Min Range: -1.3788

Max Act: 0.9437. Min Act: -0.0001

Data Index: 486117 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.0342. Min Act: -0.0001

Data Index: 1302518 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 1.3788. Min Range: -1.3788

Max Act: 0.9757. Min Act: -0.0001

Data Index: 134343 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.0108. Min Act: -0.0001

Data Index: 744528 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.0422. Min Act: -0.0001

Data Index: 110710 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 1.3788. Min Range: -1.3788

Max Act: 0.9524. Min Act: -0.0001

Data Index: 144840 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 1.3788. Min Range: -1.3788

Max Act: 1.0178. Min Act: -0.0001

Data Index: 878081 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 1.3788. Min Range: -1.3788

Max Act: 0.9459. Min Act: -0.0001

Data Index: 1061069 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 1.3788. Min Range: -1.3788

Max Act: 0.9694. Min Act: -0.0001

Data Index: 1118534 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 1.3788. Min Range: -1.3788

Max Act: 0.9650. Min Act: -0.0001

Data Index: 508553 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 1.3788. Min Range: -1.3788

Max Act: 0.9683. Min Act: -0.0001

Data Index: 821431 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 1.3788. Min Range: -1.3788

Max Act: 0.9885. Min Act: -0.0001

Data Index: 111540 (C4 (Web Text))

Max Activating Token Index: 392