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

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

Neuron 4271 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: 2.1515. Min Range: -2.1515

Max Act: 2.0476. Min Act: -0.0000

Data Index: 1617858 (Python Code)

Max Activating Token Index: 941

Text #1

Max Range: 2.1515. Min Range: -2.1515

Max Act: 1.8891. Min Act: -0.0000

Data Index: 1470623 (Python Code)

Max Activating Token Index: 604

Text #2

Max Range: 2.1515. Min Range: -2.1515

Max Act: 2.1515. Min Act: -0.0000

Data Index: 1172167 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 2.1515. Min Range: -2.1515

Max Act: 2.0921. Min Act: -0.0000

Data Index: 1535625 (Python Code)

Max Activating Token Index: 712

Text #4

Max Range: 2.1515. Min Range: -2.1515

Max Act: 1.7588. Min Act: -0.0000

Data Index: 1085641 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 2.1515. Min Range: -2.1515

Max Act: 1.9993. Min Act: -0.0000

Data Index: 1476183 (Python Code)

Max Activating Token Index: 472

Text #6

Max Range: 2.1515. Min Range: -2.1515

Max Act: 1.8330. Min Act: -0.0000

Data Index: 1480669 (Python Code)

Max Activating Token Index: 483

Text #7

Max Range: 2.1515. Min Range: -2.1515

Max Act: 1.7225. Min Act: -0.0000

Data Index: 391170 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 2.1515. Min Range: -2.1515

Max Act: 1.8621. Min Act: -0.0000

Data Index: 1461257 (Python Code)

Max Activating Token Index: 629

Text #9

Max Range: 2.1515. Min Range: -2.1515

Max Act: 1.7880. Min Act: -0.0000

Data Index: 1536083 (Python Code)

Max Activating Token Index: 824

Text #10

Max Range: 2.1515. Min Range: -2.1515

Max Act: 1.7838. Min Act: -0.0000

Data Index: 1612885 (Python Code)

Max Activating Token Index: 970

Text #11

Max Range: 2.1515. Min Range: -2.1515

Max Act: 1.9887. Min Act: -0.0000

Data Index: 1401428 (Python Code)

Max Activating Token Index: 967

Text #12

Max Range: 2.1515. Min Range: -2.1515

Max Act: 1.7657. Min Act: -0.0000

Data Index: 1590185 (Python Code)

Max Activating Token Index: 825

Text #13

Max Range: 2.1515. Min Range: -2.1515

Max Act: 1.4728. Min Act: -0.0000

Data Index: 1629981 (Python Code)

Max Activating Token Index: 65

Text #14

Max Range: 2.1515. Min Range: -2.1515

Max Act: 2.0448. Min Act: -0.0000

Data Index: 1631480 (Python Code)

Max Activating Token Index: 172

Text #15

Max Range: 2.1515. Min Range: -2.1515

Max Act: 1.7273. Min Act: -0.0000

Data Index: 1549947 (Python Code)

Max Activating Token Index: 242

Text #16

Max Range: 2.1515. Min Range: -2.1515

Max Act: 1.8177. Min Act: -0.0000

Data Index: 1617346 (Python Code)

Max Activating Token Index: 807

Text #17

Max Range: 2.1515. Min Range: -2.1515

Max Act: 1.6140. Min Act: -0.0000

Data Index: 1508337 (Python Code)

Max Activating Token Index: 978

Text #18

Max Range: 2.1515. Min Range: -2.1515

Max Act: 1.8210. Min Act: -0.0000

Data Index: 1475199 (Python Code)

Max Activating Token Index: 115

Text #19

Max Range: 2.1515. Min Range: -2.1515

Max Act: 1.6862. Min Act: -0.0000

Data Index: 1419318 (Python Code)

Max Activating Token Index: 690