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

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

Neuron 92 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: 0.5152. Min Range: -0.5152

Max Act: 0.5089. Min Act: -0.0001

Data Index: 1172094 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.5107. Min Act: -0.0001

Data Index: 749082 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.5116. Min Act: -0.0001

Data Index: 800719 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.5122. Min Act: -0.0001

Data Index: 258832 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.5087. Min Act: -0.0001

Data Index: 454767 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.5035. Min Act: -0.0001

Data Index: 1196540 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.5073. Min Act: -0.0001

Data Index: 753341 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.5152. Min Act: -0.0001

Data Index: 799803 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.5009. Min Act: -0.0001

Data Index: 1001227 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4976. Min Act: -0.0001

Data Index: 624243 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4958. Min Act: -0.0001

Data Index: 1058984 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4929. Min Act: -0.0001

Data Index: 195161 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4935. Min Act: -0.0001

Data Index: 376527 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4887. Min Act: -0.0001

Data Index: 670778 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4949. Min Act: -0.0001

Data Index: 179350 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4937. Min Act: -0.0001

Data Index: 915240 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4934. Min Act: -0.0001

Data Index: 1000452 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4970. Min Act: -0.0001

Data Index: 557035 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4980. Min Act: -0.0001

Data Index: 1097090 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4877. Min Act: -0.0001

Data Index: 320938 (C4 (Web Text))

Max Activating Token Index: 22