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

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

Neuron 3164 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.4686. Min Act: -0.0000

Data Index: 492435 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.4139. Min Act: -0.0000

Data Index: 818347 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3794. Min Act: -0.0000

Data Index: 1504249 (Python Code)

Max Activating Token Index: 147

Text #3

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3535. Min Act: -0.0000

Data Index: 419385 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1002409 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3350. Min Act: -0.0000

Data Index: 1457794 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3457. Min Act: -0.0000

Data Index: 866930 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3784. Min Act: -0.0000

Data Index: 1015099 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3297. Min Act: -0.0000

Data Index: 883012 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3401. Min Act: -0.0000

Data Index: 1291155 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1179492 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3356. Min Act: -0.0000

Data Index: 388002 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1569454 (Python Code)

Max Activating Token Index: 458

Text #13

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3124. Min Act: -0.0000

Data Index: 1373411 (Python Code)

Max Activating Token Index: 931

Text #14

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3128. Min Act: -0.0000

Data Index: 1110359 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3097. Min Act: 0.0001

Data Index: 462796 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3013. Min Act: -0.0000

Data Index: 1567427 (Python Code)

Max Activating Token Index: 738

Text #17

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.2987. Min Act: 0.0000

Data Index: 1083317 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.2964. Min Act: -0.0000

Data Index: 1113112 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3018. Min Act: -0.0000

Data Index: 1531978 (Python Code)

Max Activating Token Index: 989