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

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

Neuron 2879 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.6899. Min Act: -0.0001

Data Index: 761606 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.6066. Min Act: -0.0001

Data Index: 372933 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.6238. Min Act: -0.0001

Data Index: 681643 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.5450. Min Act: -0.0001

Data Index: 249485 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.5837. Min Act: -0.0001

Data Index: 1030093 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.5553. Min Act: -0.0001

Data Index: 1159367 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.5434. Min Act: -0.0001

Data Index: 332690 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4879. Min Act: -0.0001

Data Index: 745795 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4819. Min Act: -0.0001

Data Index: 1000468 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4925. Min Act: -0.0001

Data Index: 1008439 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4863. Min Act: -0.0001

Data Index: 224338 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4833. Min Act: -0.0001

Data Index: 62837 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.5184. Min Act: -0.0001

Data Index: 785973 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4081. Min Act: -0.0001

Data Index: 249852 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4824. Min Act: -0.0001

Data Index: 794560 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.5107. Min Act: -0.0001

Data Index: 766758 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.5862. Min Act: -0.0001

Data Index: 903709 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4434. Min Act: -0.0001

Data Index: 1012863 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4823. Min Act: -0.0001

Data Index: 242463 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4379. Min Act: -0.0001

Data Index: 1263213 (C4 (Web Text))

Max Activating Token Index: 749