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

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

Neuron 718 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: 1.0125. Min Range: -1.0125

Max Act: 1.0125. Min Act: -0.0002

Data Index: 1238047 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.9498. Min Act: -0.0002

Data Index: 1073704 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.9458. Min Act: -0.0002

Data Index: 791625 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.9387. Min Act: -0.0002

Data Index: 560307 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.9007. Min Act: -0.0003

Data Index: 47425 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8722. Min Act: -0.0002

Data Index: 1135069 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.9006. Min Act: -0.0002

Data Index: 620057 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8467. Min Act: -0.0002

Data Index: 1253548 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8700. Min Act: -0.0002

Data Index: 104524 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8590. Min Act: -0.0002

Data Index: 1355125 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8533. Min Act: -0.0002

Data Index: 1092340 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8453. Min Act: -0.0002

Data Index: 478254 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8529. Min Act: -0.0002

Data Index: 1291451 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8405. Min Act: -0.0002

Data Index: 228634 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8136. Min Act: -0.0002

Data Index: 1201780 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8213. Min Act: -0.0002

Data Index: 453326 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8086. Min Act: -0.0002

Data Index: 671038 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8238. Min Act: -0.0002

Data Index: 527497 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8208. Min Act: -0.0002

Data Index: 1127434 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8027. Min Act: -0.0002

Data Index: 328454 (C4 (Web Text))

Max Activating Token Index: 50