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

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

Neuron 3674 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.7681. Min Act: -0.0001

Data Index: 573440 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.6949. Min Act: -0.0001

Data Index: 593933 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 1.7681. Min Range: -1.7681

Max Act: 0.0254. Min Act: -0.0000

Data Index: 122752 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 1.7681. Min Range: -1.7681

Max Act: 0.0186. Min Act: -0.0001

Data Index: 1014579 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 1.7681. Min Range: -1.7681

Max Act: 0.0172. Min Act: -0.0000

Data Index: 26793 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 1.7681. Min Range: -1.7681

Max Act: 0.0174. Min Act: -0.0000

Data Index: 43317 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 1.7681. Min Range: -1.7681

Max Act: 0.0178. Min Act: -0.0000

Data Index: 178603 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.7681. Min Range: -1.7681

Max Act: 0.0170. Min Act: -0.0000

Data Index: 1184493 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 1.7681. Min Range: -1.7681

Max Act: 0.0174. Min Act: -0.0000

Data Index: 779867 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 1.7681. Min Range: -1.7681

Max Act: 0.0170. Min Act: -0.0001

Data Index: 995609 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 1.7681. Min Range: -1.7681

Max Act: 0.0166. Min Act: -0.0000

Data Index: 889183 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 1.7681. Min Range: -1.7681

Max Act: 0.0164. Min Act: -0.0000

Data Index: 220841 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 1.7681. Min Range: -1.7681

Max Act: 0.0167. Min Act: -0.0000

Data Index: 329088 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 1.7681. Min Range: -1.7681

Max Act: 0.0164. Min Act: -0.0000

Data Index: 1174251 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 1.7681. Min Range: -1.7681

Max Act: 0.0167. Min Act: -0.0000

Data Index: 861941 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 1.7681. Min Range: -1.7681

Max Act: 0.0174. Min Act: -0.0000

Data Index: 17614 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 1.7681. Min Range: -1.7681

Max Act: 0.0161. Min Act: -0.0000

Data Index: 31734 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 1.7681. Min Range: -1.7681

Max Act: 0.0159. Min Act: -0.0000

Data Index: 545326 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 1.7681. Min Range: -1.7681

Max Act: 0.0163. Min Act: -0.0001

Data Index: 1192897 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 1.7681. Min Range: -1.7681

Max Act: 0.0163. Min Act: -0.0001

Data Index: 678401 (C4 (Web Text))

Max Activating Token Index: 8