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

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

Neuron 4099 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.4184. Min Act: -0.0000

Data Index: 1308560 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3909. Min Act: -0.0000

Data Index: 673696 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3496. Min Act: -0.0000

Data Index: 479220 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3173. Min Act: -0.0001

Data Index: 920336 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3077. Min Act: -0.0001

Data Index: 483953 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.2887. Min Act: -0.0000

Data Index: 326124 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3004. Min Act: -0.0001

Data Index: 1249113 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3083. Min Act: -0.0001

Data Index: 1340149 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3003. Min Act: -0.0001

Data Index: 132228 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.2739. Min Act: -0.0001

Data Index: 513707 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.2910. Min Act: -0.0001

Data Index: 520455 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.2892. Min Act: -0.0001

Data Index: 463886 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.2767. Min Act: -0.0001

Data Index: 1138231 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.2638. Min Act: -0.0001

Data Index: 810751 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.2759. Min Act: -0.0001

Data Index: 1275922 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.2787. Min Act: -0.0000

Data Index: 1152540 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.2572. Min Act: -0.0001

Data Index: 1225482 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.2741. Min Act: -0.0001

Data Index: 106131 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.2835. Min Act: -0.0000

Data Index: 1231535 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.2846. Min Act: -0.0001

Data Index: 485716 (C4 (Web Text))

Max Activating Token Index: 4