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

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

Neuron 71 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: 0.7859. Min Range: -0.7859

Max Act: 0.7859. Min Act: -0.0002

Data Index: 1211022 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.7465. Min Act: -0.0001

Data Index: 577679 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.7327. Min Act: -0.0001

Data Index: 273057 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.7388. Min Act: -0.0001

Data Index: 633229 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.7190. Min Act: -0.0001

Data Index: 15761 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.7325. Min Act: -0.0001

Data Index: 409770 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.7126. Min Act: -0.0001

Data Index: 16827 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6988. Min Act: -0.0001

Data Index: 866756 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.7147. Min Act: -0.0001

Data Index: 198137 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.7077. Min Act: -0.0001

Data Index: 994016 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6964. Min Act: -0.0001

Data Index: 848230 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6997. Min Act: -0.0002

Data Index: 1112552 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.7090. Min Act: -0.0001

Data Index: 602568 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6926. Min Act: -0.0001

Data Index: 989717 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6963. Min Act: -0.0001

Data Index: 696041 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6817. Min Act: -0.0001

Data Index: 1217923 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6916. Min Act: -0.0001

Data Index: 1222236 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6759. Min Act: -0.0001

Data Index: 810081 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6824. Min Act: -0.0001

Data Index: 1097110 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6743. Min Act: -0.0001

Data Index: 824369 (C4 (Web Text))

Max Activating Token Index: 1023