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

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

Neuron 3966 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.7767. Min Act: -0.0001

Data Index: 642950 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.7214. Min Act: -0.0001

Data Index: 1128670 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.7182. Min Act: -0.0001

Data Index: 689877 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6687. Min Act: -0.0001

Data Index: 462269 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6990. Min Act: -0.0001

Data Index: 1114532 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6504. Min Act: -0.0001

Data Index: 657172 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6770. Min Act: -0.0001

Data Index: 265581 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6858. Min Act: -0.0001

Data Index: 49065 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6377. Min Act: -0.0001

Data Index: 1109924 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6379. Min Act: -0.0001

Data Index: 336428 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6469. Min Act: -0.0001

Data Index: 534703 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6155. Min Act: -0.0001

Data Index: 407640 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6103. Min Act: -0.0001

Data Index: 20449 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6425. Min Act: -0.0001

Data Index: 322845 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6157. Min Act: -0.0001

Data Index: 1147602 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6005. Min Act: -0.0001

Data Index: 1279070 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5911. Min Act: -0.0001

Data Index: 1324985 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5973. Min Act: -0.0001

Data Index: 127152 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5911. Min Act: -0.0001

Data Index: 408700 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6086. Min Act: -0.0001

Data Index: 1553 (C4 (Web Text))

Max Activating Token Index: 818