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

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

Neuron 5303 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: 0.5402. Min Range: -0.5402

Max Act: 0.5402. Min Act: -0.0001

Data Index: 1053196 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.5205. Min Act: -0.0001

Data Index: 617267 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.5166. Min Act: -0.0001

Data Index: 188270 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4951. Min Act: -0.0001

Data Index: 541661 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.5060. Min Act: -0.0001

Data Index: 815522 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.5014. Min Act: -0.0001

Data Index: 857618 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4964. Min Act: -0.0001

Data Index: 1242647 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4921. Min Act: -0.0001

Data Index: 910881 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4913. Min Act: -0.0001

Data Index: 704378 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4801. Min Act: -0.0001

Data Index: 209336 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4883. Min Act: -0.0001

Data Index: 444835 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4730. Min Act: -0.0001

Data Index: 1128288 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4808. Min Act: -0.0001

Data Index: 518823 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4766. Min Act: -0.0001

Data Index: 839641 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4688. Min Act: -0.0001

Data Index: 1267016 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4737. Min Act: -0.0001

Data Index: 1169588 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4771. Min Act: -0.0001

Data Index: 250188 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4775. Min Act: -0.0001

Data Index: 678755 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4697. Min Act: -0.0001

Data Index: 133734 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4755. Min Act: -0.0001

Data Index: 946900 (C4 (Web Text))

Max Activating Token Index: 8