Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1666 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.4155. Min Act: -0.0001

Data Index: 1296839 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3998. Min Act: -0.0001

Data Index: 1072680 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3904. Min Act: -0.0000

Data Index: 248128 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3862. Min Act: -0.0001

Data Index: 1293314 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3741. Min Act: -0.0001

Data Index: 118398 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1116294 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3676. Min Act: -0.0000

Data Index: 1005429 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3712. Min Act: -0.0001

Data Index: 618453 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3526. Min Act: -0.0001

Data Index: 97578 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3641. Min Act: -0.0001

Data Index: 324822 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3477. Min Act: -0.0000

Data Index: 868851 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3390. Min Act: -0.0000

Data Index: 348462 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3432. Min Act: -0.0001

Data Index: 1196004 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3540. Min Act: -0.0000

Data Index: 202707 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3500. Min Act: -0.0000

Data Index: 562183 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3388. Min Act: -0.0001

Data Index: 1055831 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3379. Min Act: -0.0000

Data Index: 1290147 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3478. Min Act: -0.0001

Data Index: 203454 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3240. Min Act: -0.0000

Data Index: 110259 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3217. Min Act: -0.0001

Data Index: 264486 (C4 (Web Text))

Max Activating Token Index: 301