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

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

Neuron 5134 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: 0.6962. Min Range: -0.6962

Max Act: 0.6962. Min Act: -0.0001

Data Index: 12005 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.6809. Min Act: -0.0001

Data Index: 806499 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.6400. Min Act: -0.0001

Data Index: 812843 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.6220. Min Act: -0.0001

Data Index: 1070415 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.6071. Min Act: -0.0001

Data Index: 1327132 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.6105. Min Act: -0.0001

Data Index: 1272229 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.6144. Min Act: -0.0002

Data Index: 787239 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.6032. Min Act: -0.0001

Data Index: 154376 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.6007. Min Act: -0.0001

Data Index: 555654 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5903. Min Act: -0.0001

Data Index: 1194181 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5801. Min Act: -0.0001

Data Index: 1228952 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5788. Min Act: -0.0002

Data Index: 1164645 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5714. Min Act: -0.0001

Data Index: 857537 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5751. Min Act: -0.0001

Data Index: 816184 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5664. Min Act: -0.0001

Data Index: 865463 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5613. Min Act: -0.0001

Data Index: 801856 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5637. Min Act: -0.0001

Data Index: 905588 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5576. Min Act: -0.0001

Data Index: 659284 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5467. Min Act: -0.0001

Data Index: 590355 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5454. Min Act: -0.0001

Data Index: 268165 (C4 (Web Text))

Max Activating Token Index: 688