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

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

Neuron 4298 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: 0.3256. Min Range: -0.3256

Max Act: 0.3256. Min Act: -0.0001

Data Index: 86391 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.3178. Min Act: -0.0001

Data Index: 1122232 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.3161. Min Act: -0.0001

Data Index: 1152954 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.3184. Min Act: -0.0001

Data Index: 818818 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.3148. Min Act: -0.0001

Data Index: 744475 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.3114. Min Act: -0.0001

Data Index: 838533 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.3160. Min Act: -0.0001

Data Index: 846718 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.3157. Min Act: -0.0001

Data Index: 431769 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.3144. Min Act: -0.0001

Data Index: 1263412 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.3038. Min Act: -0.0001

Data Index: 1175659 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.3014. Min Act: -0.0001

Data Index: 481079 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.3027. Min Act: -0.0001

Data Index: 697915 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2979. Min Act: -0.0001

Data Index: 294883 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2938. Min Act: -0.0001

Data Index: 753343 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2998. Min Act: -0.0001

Data Index: 1273182 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.3040. Min Act: -0.0001

Data Index: 718596 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2945. Min Act: -0.0001

Data Index: 1609385 (Python Code)

Max Activating Token Index: 61

Text #17

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2928. Min Act: -0.0001

Data Index: 1506982 (Python Code)

Max Activating Token Index: 5

Text #18

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2960. Min Act: -0.0001

Data Index: 270359 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2916. Min Act: -0.0001

Data Index: 72031 (C4 (Web Text))

Max Activating Token Index: 779