Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1774 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9153. Min Range: -1.9153

Max Act: 1.8254. Min Act: -0.0001

Data Index: 311586 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 1.9153. Min Range: -1.9153

Max Act: 1.9153. Min Act: -0.0001

Data Index: 982933 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 1.9153. Min Range: -1.9153

Max Act: 1.8379. Min Act: -0.0001

Data Index: 829166 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 1.9153. Min Range: -1.9153

Max Act: 1.8459. Min Act: -0.0001

Data Index: 524832 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 1.9153. Min Range: -1.9153

Max Act: 1.8651. Min Act: -0.0001

Data Index: 1122656 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 1.9153. Min Range: -1.9153

Max Act: 1.7372. Min Act: -0.0001

Data Index: 401305 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 1.9153. Min Range: -1.9153

Max Act: 1.7465. Min Act: -0.0001

Data Index: 823384 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 1.9153. Min Range: -1.9153

Max Act: 1.8073. Min Act: -0.0001

Data Index: 1292822 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 1.9153. Min Range: -1.9153

Max Act: 1.7029. Min Act: -0.0001

Data Index: 742790 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 1.9153. Min Range: -1.9153

Max Act: 1.7984. Min Act: -0.0001

Data Index: 524308 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 1.9153. Min Range: -1.9153

Max Act: 1.5828. Min Act: -0.0001

Data Index: 1065357 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 1.9153. Min Range: -1.9153

Max Act: 1.5679. Min Act: -0.0001

Data Index: 672265 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 1.9153. Min Range: -1.9153

Max Act: 1.3997. Min Act: -0.0001

Data Index: 1621068 (Python Code)

Max Activating Token Index: 770

Text #13

Max Range: 1.9153. Min Range: -1.9153

Max Act: 1.6144. Min Act: -0.0001

Data Index: 1086571 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 1.9153. Min Range: -1.9153

Max Act: 1.8785. Min Act: -0.0001

Data Index: 186599 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 1.9153. Min Range: -1.9153

Max Act: 1.4993. Min Act: -0.0001

Data Index: 801204 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 1.9153. Min Range: -1.9153

Max Act: 1.5580. Min Act: -0.0001

Data Index: 1206953 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 1.9153. Min Range: -1.9153

Max Act: 1.4798. Min Act: -0.0001

Data Index: 1280789 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 1.9153. Min Range: -1.9153

Max Act: 1.4156. Min Act: -0.0001

Data Index: 923442 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 1.9153. Min Range: -1.9153

Max Act: 1.5440. Min Act: -0.0001

Data Index: 498592 (C4 (Web Text))

Max Activating Token Index: 910