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

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

Neuron 68 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.3681. Min Act: -0.0000

Data Index: 718910 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.3385. Min Act: -0.0000

Data Index: 365721 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.3345. Min Act: -0.0000

Data Index: 86414 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.3174. Min Act: -0.0000

Data Index: 624716 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2957. Min Act: -0.0000

Data Index: 247367 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.3124. Min Act: -0.0000

Data Index: 218831 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2882. Min Act: -0.0000

Data Index: 1061353 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.3135. Min Act: -0.0000

Data Index: 569240 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1000908 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2876. Min Act: -0.0000

Data Index: 958482 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2973. Min Act: -0.0000

Data Index: 700035 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.3072. Min Act: -0.0000

Data Index: 381822 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.3054. Min Act: -0.0000

Data Index: 786982 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.3019. Min Act: -0.0000

Data Index: 432863 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2930. Min Act: -0.0000

Data Index: 991392 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.3016. Min Act: -0.0000

Data Index: 618639 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2895. Min Act: -0.0000

Data Index: 274037 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2824. Min Act: -0.0000

Data Index: 179675 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1028108 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2899. Min Act: -0.0000

Data Index: 165026 (C4 (Web Text))

Max Activating Token Index: 253