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

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

Neuron 3418 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: 0.0578. Min Range: -0.0578

Max Act: 0.0578. Min Act: -0.0001

Data Index: 1249357 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0520. Min Act: -0.0001

Data Index: 24382 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0518. Min Act: -0.0001

Data Index: 977084 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0498. Min Act: -0.0001

Data Index: 702217 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0484. Min Act: -0.0001

Data Index: 522061 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0458. Min Act: -0.0001

Data Index: 692040 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1285516 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0457. Min Act: -0.0001

Data Index: 542029 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0444. Min Act: -0.0001

Data Index: 1087305 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0445. Min Act: -0.0001

Data Index: 571584 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0444. Min Act: -0.0001

Data Index: 1070471 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0453. Min Act: -0.0001

Data Index: 964007 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1161882 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0431. Min Act: -0.0001

Data Index: 987229 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0433. Min Act: -0.0001

Data Index: 764613 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0432. Min Act: -0.0001

Data Index: 589 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0430. Min Act: -0.0001

Data Index: 977823 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0439. Min Act: -0.0001

Data Index: 1196025 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0436. Min Act: -0.0001

Data Index: 113451 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0431. Min Act: -0.0001

Data Index: 972837 (C4 (Web Text))

Max Activating Token Index: 1023