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

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

Neuron 2376 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.3068. Min Act: -0.0001

Data Index: 97547 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.3127. Min Act: -0.0001

Data Index: 344443 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.3170. Min Act: -0.0001

Data Index: 140413 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2890. Min Act: -0.0001

Data Index: 682087 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2716. Min Act: -0.0001

Data Index: 852660 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2612. Min Act: -0.0001

Data Index: 52707 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.3194. Min Act: -0.0001

Data Index: 1013842 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2520. Min Act: -0.0001

Data Index: 109912 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2381. Min Act: -0.0001

Data Index: 373518 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2466. Min Act: -0.0001

Data Index: 200947 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2450. Min Act: -0.0001

Data Index: 718385 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2532. Min Act: -0.0001

Data Index: 583712 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2429. Min Act: -0.0001

Data Index: 1060717 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2503. Min Act: -0.0001

Data Index: 747195 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2508. Min Act: -0.0001

Data Index: 1014340 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2505. Min Act: -0.0001

Data Index: 772047 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2478. Min Act: -0.0001

Data Index: 589119 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2468. Min Act: -0.0001

Data Index: 992167 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2405. Min Act: -0.0001

Data Index: 1135787 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2553. Min Act: -0.0001

Data Index: 1045590 (C4 (Web Text))

Max Activating Token Index: 281