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

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

Neuron 562 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: 0.6453. Min Range: -0.6453

Max Act: 0.6419. Min Act: -0.0001

Data Index: 272063 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.6453. Min Act: -0.0001

Data Index: 1357979 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.6204. Min Act: -0.0001

Data Index: 148187 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.6218. Min Act: -0.0001

Data Index: 899914 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.6221. Min Act: -0.0001

Data Index: 403676 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.6112. Min Act: -0.0001

Data Index: 287906 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.6024. Min Act: -0.0001

Data Index: 58824 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5909. Min Act: -0.0001

Data Index: 1167391 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5879. Min Act: -0.0001

Data Index: 1280186 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5817. Min Act: -0.0001

Data Index: 1289335 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5810. Min Act: -0.0001

Data Index: 560382 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5786. Min Act: -0.0001

Data Index: 496023 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5846. Min Act: -0.0001

Data Index: 783810 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5894. Min Act: -0.0001

Data Index: 1106154 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5890. Min Act: -0.0001

Data Index: 1065396 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5829. Min Act: -0.0001

Data Index: 291186 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5753. Min Act: -0.0001

Data Index: 358475 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5699. Min Act: -0.0001

Data Index: 684790 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5869. Min Act: -0.0001

Data Index: 1300630 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5811. Min Act: -0.0001

Data Index: 433900 (C4 (Web Text))

Max Activating Token Index: 506