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

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

Neuron 5590 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: 1.6299. Min Range: -1.6299

Max Act: 1.6299. Min Act: -0.0002

Data Index: 187890 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.5388. Min Act: -0.0002

Data Index: 1272518 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.5263. Min Act: -0.0002

Data Index: 241270 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.5223. Min Act: -0.0002

Data Index: 800561 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.4832. Min Act: -0.0002

Data Index: 762778 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.4510. Min Act: -0.0002

Data Index: 1048334 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.4428. Min Act: -0.0002

Data Index: 926088 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.4374. Min Act: -0.0002

Data Index: 1009431 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.3863. Min Act: -0.0002

Data Index: 475387 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.3464. Min Act: -0.0003

Data Index: 309578 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.3192. Min Act: -0.0002

Data Index: 370006 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.3114. Min Act: -0.0002

Data Index: 984667 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.2844. Min Act: -0.0002

Data Index: 69411 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.3059. Min Act: -0.0002

Data Index: 704120 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.2856. Min Act: -0.0002

Data Index: 650285 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.2893. Min Act: -0.0002

Data Index: 1071386 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.2808. Min Act: -0.0002

Data Index: 134243 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.2634. Min Act: -0.0002

Data Index: 188674 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.2515. Min Act: -0.0002

Data Index: 537630 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.2726. Min Act: -0.0003

Data Index: 309436 (C4 (Web Text))

Max Activating Token Index: 480