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

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

Neuron 3425 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: 1.3174. Min Range: -1.3174

Max Act: 1.3174. Min Act: -0.0000

Data Index: 2402 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 1.3174. Min Range: -1.3174

Max Act: 1.2427. Min Act: -0.0000

Data Index: 835736 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 1.3174. Min Range: -1.3174

Max Act: 1.0619. Min Act: -0.0000

Data Index: 327746 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 1.3174. Min Range: -1.3174

Max Act: 1.0861. Min Act: -0.0000

Data Index: 364058 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 1.3174. Min Range: -1.3174

Max Act: 1.0508. Min Act: -0.0000

Data Index: 123228 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 1.3174. Min Range: -1.3174

Max Act: 1.0285. Min Act: -0.0000

Data Index: 1302482 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 1.3174. Min Range: -1.3174

Max Act: 1.0058. Min Act: -0.0000

Data Index: 464308 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 1.3174. Min Range: -1.3174

Max Act: 0.9076. Min Act: -0.0000

Data Index: 448219 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 1.3174. Min Range: -1.3174

Max Act: 0.9118. Min Act: -0.0000

Data Index: 1254146 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 1.3174. Min Range: -1.3174

Max Act: 0.9081. Min Act: -0.0000

Data Index: 1183499 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 1.3174. Min Range: -1.3174

Max Act: 0.8691. Min Act: -0.0000

Data Index: 877533 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 1.3174. Min Range: -1.3174

Max Act: 0.9148. Min Act: -0.0000

Data Index: 903839 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 1.3174. Min Range: -1.3174

Max Act: 0.9144. Min Act: -0.0000

Data Index: 794937 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 1.3174. Min Range: -1.3174

Max Act: 0.8529. Min Act: -0.0000

Data Index: 154231 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 1.3174. Min Range: -1.3174

Max Act: 0.8880. Min Act: -0.0000

Data Index: 918862 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 1.3174. Min Range: -1.3174

Max Act: 0.8585. Min Act: -0.0000

Data Index: 932282 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 1.3174. Min Range: -1.3174

Max Act: 0.8550. Min Act: -0.0000

Data Index: 515905 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 1.3174. Min Range: -1.3174

Max Act: 0.8517. Min Act: -0.0000

Data Index: 76399 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 1.3174. Min Range: -1.3174

Max Act: 0.8146. Min Act: -0.0000

Data Index: 146651 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 1.3174. Min Range: -1.3174

Max Act: 0.8383. Min Act: -0.0000

Data Index: 1470008 (Python Code)

Max Activating Token Index: 128