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

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

Neuron 5162 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: 0.2293. Min Range: -0.2293

Max Act: 0.2293. Min Act: -0.0001

Data Index: 114069 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.0726. Min Act: -0.0001

Data Index: 280230 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.0725. Min Act: -0.0001

Data Index: 633881 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1096656 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.0649. Min Act: -0.0001

Data Index: 207930 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.0643. Min Act: -0.0001

Data Index: 25182 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.0658. Min Act: -0.0001

Data Index: 1090143 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.0640. Min Act: -0.0001

Data Index: 177101 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.0639. Min Act: -0.0001

Data Index: 1252359 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.0613. Min Act: -0.0001

Data Index: 917710 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.0612. Min Act: -0.0001

Data Index: 1019113 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.0637. Min Act: -0.0001

Data Index: 176559 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.0608. Min Act: -0.0001

Data Index: 902530 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1300112 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.0608. Min Act: -0.0001

Data Index: 149519 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.0609. Min Act: -0.0001

Data Index: 188704 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.0602. Min Act: -0.0001

Data Index: 397590 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1084697 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.0603. Min Act: -0.0001

Data Index: 1356530 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.0602. Min Act: -0.0001

Data Index: 199508 (C4 (Web Text))

Max Activating Token Index: 168