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

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

Neuron 5866 in Layer 1

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: 1.9862. Min Range: -1.9862

Max Act: 1.9862. Min Act: -0.0002

Data Index: 866771 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.9714. Min Act: -0.0002

Data Index: 1019423 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.8542. Min Act: -0.0002

Data Index: 1342567 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.9023. Min Act: -0.0002

Data Index: 440337 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.9119. Min Act: -0.0002

Data Index: 229359 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.8886. Min Act: -0.0002

Data Index: 1347060 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.8338. Min Act: -0.0003

Data Index: 1073028 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.8139. Min Act: -0.0003

Data Index: 974899 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.8168. Min Act: -0.0002

Data Index: 575792 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.8094. Min Act: -0.0002

Data Index: 216525 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.7810. Min Act: -0.0002

Data Index: 1100920 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.7379. Min Act: -0.0002

Data Index: 257876 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.7222. Min Act: -0.0002

Data Index: 554863 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.6948. Min Act: -0.0002

Data Index: 396248 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.7241. Min Act: -0.0002

Data Index: 854263 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.7052. Min Act: -0.0002

Data Index: 37463 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.7484. Min Act: -0.0002

Data Index: 1326151 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.6560. Min Act: -0.0003

Data Index: 63969 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.6968. Min Act: -0.0002

Data Index: 1271151 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 1.9862. Min Range: -1.9862

Max Act: 1.7339. Min Act: -0.0002

Data Index: 98959 (C4 (Web Text))

Max Activating Token Index: 218