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

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

Neuron 675 in Layer 1

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: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1202401 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 804629 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1456219 (Python Code)

Max Activating Token Index: 985

Text #3

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1129928 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1113505 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 179980 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 382921 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 315922 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 904019 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 40267 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 745709 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 615527 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1279368 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1211143 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1051306 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 637154 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 865786 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 98180 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1187515 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1344248 (C4 (Web Text))

Max Activating Token Index: 860