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

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

Neuron 187 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.7538. Min Act: -0.0000

Data Index: 1000521 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.5786. Min Act: -0.0000

Data Index: 1346704 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6399. Min Act: -0.0000

Data Index: 991139 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6081. Min Act: -0.0000

Data Index: 472420 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.5690. Min Act: 0.0000

Data Index: 284755 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.5607. Min Act: -0.0000

Data Index: 270081 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.4292. Min Act: -0.0000

Data Index: 546262 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.4964. Min Act: 0.0000

Data Index: 1029852 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.4137. Min Act: -0.0000

Data Index: 794254 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.3431. Min Act: 0.0000

Data Index: 1138333 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.3784. Min Act: -0.0000

Data Index: 324689 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.5021. Min Act: -0.0000

Data Index: 208329 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.3240. Min Act: 0.0001

Data Index: 258491 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.5101. Min Act: 0.0001

Data Index: 1212711 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.3363. Min Act: -0.0001

Data Index: 607371 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.2628. Min Act: 0.0000

Data Index: 151943 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.2688. Min Act: -0.0000

Data Index: 332383 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.2564. Min Act: -0.0000

Data Index: 1101055 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.2963. Min Act: -0.0000

Data Index: 1354875 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.1897. Min Act: 0.0001

Data Index: 722235 (C4 (Web Text))

Max Activating Token Index: 192