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

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

Neuron 716 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.3083. Min Act: -0.0000

Data Index: 1252441 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2893. Min Act: -0.0000

Data Index: 826397 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2663. Min Act: -0.0000

Data Index: 900632 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2540. Min Act: -0.0000

Data Index: 813131 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2491. Min Act: -0.0000

Data Index: 674560 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2437. Min Act: -0.0000

Data Index: 404009 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2538. Min Act: 0.0000

Data Index: 716445 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2448. Min Act: -0.0000

Data Index: 1240007 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2212. Min Act: -0.0000

Data Index: 455943 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2277. Min Act: -0.0000

Data Index: 160499 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2335. Min Act: -0.0000

Data Index: 1132077 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2228. Min Act: -0.0000

Data Index: 1023774 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2187. Min Act: -0.0000

Data Index: 1014315 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2182. Min Act: -0.0000

Data Index: 65219 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2100. Min Act: -0.0000

Data Index: 388708 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2218. Min Act: -0.0000

Data Index: 420747 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2081. Min Act: -0.0000

Data Index: 916578 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2057. Min Act: 0.0000

Data Index: 1146105 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2055. Min Act: -0.0000

Data Index: 648879 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2105. Min Act: -0.0000

Data Index: 361068 (C4 (Web Text))

Max Activating Token Index: 89