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

Dataset: The Pile

Neuron 2826 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0936. Min Range: -3.0936

Max Act: 2.9181. Min Act: -0.0000

Data Index: 1189277 (The Pile)

Max Activating Token Index: 297

Text #1

Max Range: 3.0936. Min Range: -3.0936

Max Act: 3.0936. Min Act: -0.0000

Data Index: 779245 (The Pile)

Max Activating Token Index: 523

Text #2

Max Range: 3.0936. Min Range: -3.0936

Max Act: 2.6316. Min Act: -0.0000

Data Index: 1399481 (The Pile)

Max Activating Token Index: 661

Text #3

Max Range: 3.0936. Min Range: -3.0936

Max Act: 2.8032. Min Act: -0.0000

Data Index: 696708 (The Pile)

Max Activating Token Index: 334

Text #4

Max Range: 3.0936. Min Range: -3.0936

Max Act: 2.9293. Min Act: -0.0000

Data Index: 1881275 (The Pile)

Max Activating Token Index: 299

Text #5

Max Range: 3.0936. Min Range: -3.0936

Max Act: 2.7496. Min Act: -0.0000

Data Index: 1622079 (The Pile)

Max Activating Token Index: 723

Text #6

Max Range: 3.0936. Min Range: -3.0936

Max Act: 2.7617. Min Act: -0.0000

Data Index: 1601755 (The Pile)

Max Activating Token Index: 734

Text #7

Max Range: 3.0936. Min Range: -3.0936

Max Act: 2.8065. Min Act: -0.0000

Data Index: 344705 (The Pile)

Max Activating Token Index: 511

Text #8

Max Range: 3.0936. Min Range: -3.0936

Max Act: 1.4807. Min Act: -0.0000

Data Index: 685890 (The Pile)

Max Activating Token Index: 515

Text #9

Max Range: 3.0936. Min Range: -3.0936

Max Act: 1.4014. Min Act: -0.0000

Data Index: 1105787 (The Pile)

Max Activating Token Index: 936

Text #10

Max Range: 3.0936. Min Range: -3.0936

Max Act: 1.5054. Min Act: -0.0001

Data Index: 1262143 (The Pile)

Max Activating Token Index: 444

Text #11

Max Range: 3.0936. Min Range: -3.0936

Max Act: 1.4250. Min Act: -0.0000

Data Index: 640045 (The Pile)

Max Activating Token Index: 945

Text #12

Max Range: 3.0936. Min Range: -3.0936

Max Act: 1.3465. Min Act: -0.0000

Data Index: 459096 (The Pile)

Max Activating Token Index: 286

Text #13

Max Range: 3.0936. Min Range: -3.0936

Max Act: 1.2781. Min Act: -0.0000

Data Index: 797375 (The Pile)

Max Activating Token Index: 887

Text #14

Max Range: 3.0936. Min Range: -3.0936

Max Act: 1.2520. Min Act: -0.0000

Data Index: 198397 (The Pile)

Max Activating Token Index: 255

Text #15

Max Range: 3.0936. Min Range: -3.0936

Max Act: 1.3210. Min Act: -0.0000

Data Index: 594768 (The Pile)

Max Activating Token Index: 415

Text #16

Max Range: 3.0936. Min Range: -3.0936

Max Act: 1.3419. Min Act: -0.0000

Data Index: 1044397 (The Pile)

Max Activating Token Index: 853

Text #17

Max Range: 3.0936. Min Range: -3.0936

Max Act: 1.2604. Min Act: -0.0000

Data Index: 1710159 (The Pile)

Max Activating Token Index: 272

Text #18

Max Range: 3.0936. Min Range: -3.0936

Max Act: 1.2260. Min Act: -0.0000

Data Index: 1239770 (The Pile)

Max Activating Token Index: 757

Text #19

Max Range: 3.0936. Min Range: -3.0936

Max Act: 1.4129. Min Act: -0.0000

Data Index: 175081 (The Pile)

Max Activating Token Index: 142