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

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

Neuron 2300 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.6127. Min Act: -0.0001

Data Index: 906190 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5900. Min Act: -0.0001

Data Index: 288964 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.6082. Min Act: -0.0001

Data Index: 948103 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5844. Min Act: -0.0001

Data Index: 1282582 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5754. Min Act: -0.0002

Data Index: 261726 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5857. Min Act: -0.0001

Data Index: 1272362 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5834. Min Act: -0.0001

Data Index: 711925 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5779. Min Act: -0.0001

Data Index: 1283344 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5769. Min Act: -0.0001

Data Index: 1476542 (Python Code)

Max Activating Token Index: 909

Text #9

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5652. Min Act: -0.0001

Data Index: 127437 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5562. Min Act: -0.0001

Data Index: 962153 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5558. Min Act: -0.0001

Data Index: 959389 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5563. Min Act: -0.0001

Data Index: 1536609 (Python Code)

Max Activating Token Index: 752

Text #13

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5546. Min Act: -0.0001

Data Index: 1508183 (Python Code)

Max Activating Token Index: 457

Text #14

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5506. Min Act: -0.0001

Data Index: 1587779 (Python Code)

Max Activating Token Index: 78

Text #15

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5644. Min Act: -0.0001

Data Index: 1081109 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5484. Min Act: -0.0001

Data Index: 164381 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5516. Min Act: -0.0001

Data Index: 1556031 (Python Code)

Max Activating Token Index: 123

Text #18

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5637. Min Act: -0.0001

Data Index: 1144326 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5519. Min Act: -0.0001

Data Index: 1511934 (Python Code)

Max Activating Token Index: 824