Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2805 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.9470. Min Act: -0.0004

Data Index: 613099 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 1.0449. Min Range: -1.0449

Max Act: 1.0137. Min Act: -0.0004

Data Index: 993505 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.8746. Min Act: -0.0004

Data Index: 438362 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.9176. Min Act: -0.0004

Data Index: 367977 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.8851. Min Act: -0.0004

Data Index: 491113 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.8839. Min Act: -0.0004

Data Index: 436458 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 1.0449. Min Range: -1.0449

Max Act: 1.0017. Min Act: -0.0004

Data Index: 675821 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.8722. Min Act: -0.0004

Data Index: 850248 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.7936. Min Act: -0.0004

Data Index: 525238 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 1.0449. Min Range: -1.0449

Max Act: 1.0082. Min Act: -0.0004

Data Index: 679896 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.8406. Min Act: -0.0004

Data Index: 441304 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.9135. Min Act: -0.0004

Data Index: 1298074 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.9016. Min Act: -0.0004

Data Index: 1161415 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 1.0449. Min Range: -1.0449

Max Act: 1.0449. Min Act: -0.0004

Data Index: 1156113 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.8979. Min Act: -0.0004

Data Index: 241486 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.8866. Min Act: -0.0004

Data Index: 104873 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.8552. Min Act: -0.0004

Data Index: 63108 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.9431. Min Act: -0.0004

Data Index: 1216491 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.8584. Min Act: -0.0004

Data Index: 495868 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.7050. Min Act: -0.0004

Data Index: 211052 (C4 (Web Text))

Max Activating Token Index: 117