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

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

Neuron 1464 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.3753. Min Act: -0.0001

Data Index: 1303780 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.3417. Min Act: -0.0001

Data Index: 1130671 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.3410. Min Act: -0.0001

Data Index: 110494 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.3185. Min Act: -0.0001

Data Index: 851911 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.3250. Min Act: -0.0001

Data Index: 904726 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.3153. Min Act: -0.0001

Data Index: 362906 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.3174. Min Act: -0.0001

Data Index: 1164726 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2958. Min Act: -0.0001

Data Index: 1145767 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2967. Min Act: -0.0001

Data Index: 118268 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2983. Min Act: -0.0001

Data Index: 438955 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2899. Min Act: -0.0001

Data Index: 873141 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.3079. Min Act: -0.0001

Data Index: 886203 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2967. Min Act: -0.0001

Data Index: 304648 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.3067. Min Act: -0.0001

Data Index: 1354085 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2938. Min Act: -0.0001

Data Index: 228112 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2984. Min Act: -0.0001

Data Index: 41969 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2800. Min Act: -0.0001

Data Index: 529162 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2822. Min Act: -0.0001

Data Index: 861305 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2878. Min Act: -0.0001

Data Index: 350299 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2949. Min Act: -0.0001

Data Index: 343780 (C4 (Web Text))

Max Activating Token Index: 600