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

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

Neuron 4008 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6104. Min Range: -0.6104

Max Act: 0.6104. Min Act: -0.0001

Data Index: 778987 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.6104. Min Range: -0.6104

Max Act: 0.5913. Min Act: -0.0001

Data Index: 524210 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 0.6104. Min Range: -0.6104

Max Act: 0.5839. Min Act: -0.0001

Data Index: 1279439 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.6104. Min Range: -0.6104

Max Act: 0.5891. Min Act: -0.0001

Data Index: 619966 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.6104. Min Range: -0.6104

Max Act: 0.5855. Min Act: -0.0001

Data Index: 1115045 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.6104. Min Range: -0.6104

Max Act: 0.6059. Min Act: -0.0001

Data Index: 1107151 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 0.6104. Min Range: -0.6104

Max Act: 0.5525. Min Act: -0.0001

Data Index: 912578 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.6104. Min Range: -0.6104

Max Act: 0.5631. Min Act: -0.0001

Data Index: 240611 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.6104. Min Range: -0.6104

Max Act: 0.5232. Min Act: -0.0001

Data Index: 776890 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.6104. Min Range: -0.6104

Max Act: 0.5583. Min Act: -0.0001

Data Index: 159177 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.6104. Min Range: -0.6104

Max Act: 0.5432. Min Act: -0.0001

Data Index: 216447 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 0.6104. Min Range: -0.6104

Max Act: 0.5347. Min Act: -0.0001

Data Index: 193137 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.6104. Min Range: -0.6104

Max Act: 0.5374. Min Act: -0.0001

Data Index: 1215980 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 0.6104. Min Range: -0.6104

Max Act: 0.5693. Min Act: -0.0001

Data Index: 200238 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.6104. Min Range: -0.6104

Max Act: 0.5273. Min Act: -0.0001

Data Index: 442760 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.6104. Min Range: -0.6104

Max Act: 0.5355. Min Act: -0.0001

Data Index: 1049193 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 0.6104. Min Range: -0.6104

Max Act: 0.5591. Min Act: -0.0001

Data Index: 653815 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 0.6104. Min Range: -0.6104

Max Act: 0.5406. Min Act: -0.0001

Data Index: 1124523 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.6104. Min Range: -0.6104

Max Act: 0.5182. Min Act: -0.0001

Data Index: 131855 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.6104. Min Range: -0.6104

Max Act: 0.5506. Min Act: -0.0001

Data Index: 742312 (C4 (Web Text))

Max Activating Token Index: 664