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

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

Neuron 2984 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.8392. Min Act: -0.0001

Data Index: 509852 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.8270. Min Act: -0.0001

Data Index: 507887 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.8239. Min Act: -0.0001

Data Index: 693375 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.8028. Min Act: -0.0001

Data Index: 825604 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.8010. Min Act: -0.0001

Data Index: 1142488 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.8026. Min Act: -0.0001

Data Index: 200995 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7942. Min Act: -0.0002

Data Index: 204024 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7894. Min Act: -0.0001

Data Index: 1152450 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7858. Min Act: -0.0001

Data Index: 994669 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7919. Min Act: -0.0001

Data Index: 550277 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7966. Min Act: -0.0001

Data Index: 212188 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7969. Min Act: -0.0001

Data Index: 774672 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7889. Min Act: -0.0001

Data Index: 906738 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7830. Min Act: -0.0001

Data Index: 943680 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7908. Min Act: -0.0001

Data Index: 1242791 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7895. Min Act: -0.0001

Data Index: 21924 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7807. Min Act: -0.0001

Data Index: 184784 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7850. Min Act: -0.0001

Data Index: 1291813 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7664. Min Act: -0.0001

Data Index: 454123 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.8392. Min Range: -0.8392

Max Act: 0.7633. Min Act: -0.0001

Data Index: 974077 (C4 (Web Text))

Max Activating Token Index: 1023