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

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

Neuron 5496 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: 0.9649. Min Range: -0.9649

Max Act: 0.9598. Min Act: -0.0001

Data Index: 1222061 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9613. Min Act: -0.0001

Data Index: 716820 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9545. Min Act: -0.0001

Data Index: 109983 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9557. Min Act: -0.0001

Data Index: 1237206 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9601. Min Act: -0.0001

Data Index: 959343 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9649. Min Act: -0.0001

Data Index: 1221292 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9494. Min Act: -0.0001

Data Index: 183554 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9375. Min Act: -0.0001

Data Index: 941410 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9470. Min Act: -0.0001

Data Index: 387677 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9460. Min Act: -0.0001

Data Index: 558769 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9400. Min Act: -0.0001

Data Index: 988451 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9226. Min Act: -0.0001

Data Index: 736047 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9201. Min Act: -0.0002

Data Index: 815082 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9255. Min Act: -0.0001

Data Index: 333144 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9283. Min Act: -0.0002

Data Index: 827310 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9200. Min Act: -0.0001

Data Index: 771660 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9139. Min Act: -0.0001

Data Index: 423515 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9187. Min Act: -0.0001

Data Index: 984295 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9098. Min Act: -0.0001

Data Index: 1312266 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9145. Min Act: -0.0001

Data Index: 829397 (C4 (Web Text))

Max Activating Token Index: 1023