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

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

Neuron 2593 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: 0.4156. Min Range: -0.4156

Max Act: 0.4156. Min Act: -0.0001

Data Index: 151347 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2837. Min Act: -0.0001

Data Index: 363469 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.3474. Min Act: -0.0001

Data Index: 99084 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.3381. Min Act: -0.0001

Data Index: 679340 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.3129. Min Act: -0.0001

Data Index: 258912 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2916. Min Act: -0.0001

Data Index: 537611 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.3138. Min Act: -0.0001

Data Index: 250483 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.3030. Min Act: -0.0001

Data Index: 232693 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.3083. Min Act: -0.0001

Data Index: 958386 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.3090. Min Act: -0.0001

Data Index: 593457 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2865. Min Act: -0.0001

Data Index: 53989 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.3075. Min Act: -0.0001

Data Index: 890527 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2718. Min Act: -0.0001

Data Index: 645253 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2866. Min Act: -0.0001

Data Index: 435114 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2960. Min Act: -0.0001

Data Index: 367365 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2886. Min Act: -0.0001

Data Index: 1294938 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2782. Min Act: -0.0001

Data Index: 892308 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2750. Min Act: -0.0001

Data Index: 1321016 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2856. Min Act: -0.0001

Data Index: 449492 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2659. Min Act: -0.0001

Data Index: 211329 (C4 (Web Text))

Max Activating Token Index: 39