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

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

Neuron 5088 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: 0.6017. Min Range: -0.6017

Max Act: 0.6017. Min Act: -0.0001

Data Index: 1128521 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5412. Min Act: -0.0001

Data Index: 1274235 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5456. Min Act: -0.0001

Data Index: 579554 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5529. Min Act: -0.0001

Data Index: 777078 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5502. Min Act: -0.0001

Data Index: 474 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5397. Min Act: -0.0001

Data Index: 66085 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5430. Min Act: -0.0001

Data Index: 977325 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5315. Min Act: -0.0001

Data Index: 305645 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5277. Min Act: -0.0001

Data Index: 1207566 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5268. Min Act: -0.0001

Data Index: 245328 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5279. Min Act: -0.0001

Data Index: 984719 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5153. Min Act: -0.0001

Data Index: 519623 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5192. Min Act: -0.0001

Data Index: 108159 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5108. Min Act: -0.0001

Data Index: 985124 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5152. Min Act: -0.0001

Data Index: 291020 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5227. Min Act: -0.0001

Data Index: 1212004 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5088. Min Act: -0.0001

Data Index: 872588 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5084. Min Act: -0.0001

Data Index: 1043811 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5115. Min Act: -0.0001

Data Index: 830032 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5032. Min Act: -0.0001

Data Index: 1307586 (C4 (Web Text))

Max Activating Token Index: 239