Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 605 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3595. Min Act: -0.0000

Data Index: 49044 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3283. Min Act: -0.0001

Data Index: 946968 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3392. Min Act: -0.0000

Data Index: 1357071 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3139. Min Act: -0.0001

Data Index: 1093803 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3314. Min Act: -0.0000

Data Index: 172967 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3293. Min Act: -0.0001

Data Index: 769160 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3147. Min Act: -0.0000

Data Index: 1283289 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3147. Min Act: -0.0001

Data Index: 716458 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3196. Min Act: -0.0001

Data Index: 763265 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3084. Min Act: -0.0001

Data Index: 1120714 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3076. Min Act: -0.0001

Data Index: 774452 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3009. Min Act: -0.0001

Data Index: 458572 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2868. Min Act: -0.0000

Data Index: 1081998 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3013. Min Act: -0.0001

Data Index: 239120 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2985. Min Act: -0.0001

Data Index: 131065 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2926. Min Act: -0.0000

Data Index: 976869 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2728. Min Act: 0.0001

Data Index: 697598 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2906. Min Act: -0.0000

Data Index: 499987 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2887. Min Act: -0.0001

Data Index: 432611 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2741. Min Act: 0.0001

Data Index: 65818 (C4 (Web Text))

Max Activating Token Index: 169