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

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

Neuron 3718 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9458. Min Range: -2.9458

Max Act: 2.9458. Min Act: -0.0000

Data Index: 780304 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 2.9458. Min Range: -2.9458

Max Act: 2.6348. Min Act: -0.0000

Data Index: 685239 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 2.9458. Min Range: -2.9458

Max Act: 2.7104. Min Act: -0.0000

Data Index: 270823 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 2.9458. Min Range: -2.9458

Max Act: 2.5644. Min Act: -0.0000

Data Index: 174968 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 2.9458. Min Range: -2.9458

Max Act: 2.4942. Min Act: -0.0000

Data Index: 681749 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 2.9458. Min Range: -2.9458

Max Act: 2.2099. Min Act: -0.0000

Data Index: 1030198 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 2.9458. Min Range: -2.9458

Max Act: 2.4399. Min Act: -0.0000

Data Index: 691056 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 2.9458. Min Range: -2.9458

Max Act: 2.4493. Min Act: -0.0000

Data Index: 1313163 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 2.9458. Min Range: -2.9458

Max Act: 2.2984. Min Act: -0.0000

Data Index: 1220541 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 2.9458. Min Range: -2.9458

Max Act: 2.2525. Min Act: -0.0000

Data Index: 523757 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 2.9458. Min Range: -2.9458

Max Act: 2.3613. Min Act: -0.0000

Data Index: 396391 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 2.9458. Min Range: -2.9458

Max Act: 2.3649. Min Act: -0.0000

Data Index: 942914 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 2.9458. Min Range: -2.9458

Max Act: 2.4618. Min Act: -0.0000

Data Index: 57269 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 2.9458. Min Range: -2.9458

Max Act: 2.2162. Min Act: -0.0000

Data Index: 931224 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 2.9458. Min Range: -2.9458

Max Act: 2.1005. Min Act: -0.0000

Data Index: 743815 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 2.9458. Min Range: -2.9458

Max Act: 2.2068. Min Act: -0.0000

Data Index: 40089 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 2.9458. Min Range: -2.9458

Max Act: 2.3774. Min Act: -0.0000

Data Index: 1257609 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 2.9458. Min Range: -2.9458

Max Act: 2.2434. Min Act: -0.0000

Data Index: 791577 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 2.9458. Min Range: -2.9458

Max Act: 2.2197. Min Act: -0.0000

Data Index: 742353 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 2.9458. Min Range: -2.9458

Max Act: 2.3241. Min Act: -0.0000

Data Index: 408004 (C4 (Web Text))

Max Activating Token Index: 73