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

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

Neuron 2102 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.9510. Min Act: -0.0000

Data Index: 1076591 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.8742. Min Act: -0.0000

Data Index: 45722 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.8427. Min Act: -0.0000

Data Index: 717048 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.7525. Min Act: -0.0000

Data Index: 453242 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.6649. Min Act: -0.0000

Data Index: 563760 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.6673. Min Act: -0.0000

Data Index: 675870 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.6553. Min Act: -0.0000

Data Index: 495611 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1613521 (Python Code)

Max Activating Token Index: 76

Text #8

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.6052. Min Act: -0.0000

Data Index: 942075 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1024135 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.5889. Min Act: -0.0000

Data Index: 382389 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.5669. Min Act: -0.0000

Data Index: 750785 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.5880. Min Act: -0.0000

Data Index: 1093059 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.5854. Min Act: -0.0000

Data Index: 841243 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.5209. Min Act: -0.0000

Data Index: 1642640 (Python Code)

Max Activating Token Index: 94

Text #15

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.5888. Min Act: -0.0000

Data Index: 77253 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1494141 (Python Code)

Max Activating Token Index: 269

Text #17

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.5560. Min Act: -0.0000

Data Index: 405087 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.4913. Min Act: -0.0000

Data Index: 1426219 (Python Code)

Max Activating Token Index: 155

Text #19

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1445417 (Python Code)

Max Activating Token Index: 328