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

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

Neuron 5197 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: 0.3479. Min Range: -0.3479

Max Act: 0.3479. Min Act: -0.0001

Data Index: 896655 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.3344. Min Act: -0.0001

Data Index: 1145366 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.3282. Min Act: -0.0001

Data Index: 1263390 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.3272. Min Act: -0.0001

Data Index: 1050213 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.3261. Min Act: -0.0001

Data Index: 243471 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.3204. Min Act: -0.0001

Data Index: 1329620 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.3228. Min Act: -0.0001

Data Index: 404247 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.3267. Min Act: -0.0001

Data Index: 1189597 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.3234. Min Act: -0.0001

Data Index: 364699 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.3194. Min Act: -0.0001

Data Index: 1343769 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.3106. Min Act: -0.0001

Data Index: 68086 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.3112. Min Act: -0.0001

Data Index: 830288 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.3098. Min Act: -0.0002

Data Index: 729661 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.3036. Min Act: -0.0001

Data Index: 290069 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.3103. Min Act: -0.0001

Data Index: 438800 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.3046. Min Act: -0.0001

Data Index: 883654 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.3064. Min Act: -0.0001

Data Index: 1130902 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.3027. Min Act: -0.0001

Data Index: 412992 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.3002. Min Act: -0.0001

Data Index: 77489 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.3479. Min Range: -0.3479

Max Act: 0.3054. Min Act: -0.0001

Data Index: 430807 (C4 (Web Text))

Max Activating Token Index: 1023