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

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

Neuron 3636 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.9367. Min Act: -0.0001

Data Index: 550347 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.8698. Min Act: -0.0001

Data Index: 1104494 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.8113. Min Act: -0.0001

Data Index: 298782 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7132. Min Act: -0.0001

Data Index: 982792 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7843. Min Act: -0.0001

Data Index: 706961 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.8015. Min Act: -0.0001

Data Index: 1037224 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7023. Min Act: -0.0001

Data Index: 635901 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7533. Min Act: -0.0001

Data Index: 1109236 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7481. Min Act: -0.0001

Data Index: 91784 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7695. Min Act: -0.0001

Data Index: 848895 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7679. Min Act: -0.0001

Data Index: 360685 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.6996. Min Act: -0.0001

Data Index: 1141107 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7586. Min Act: -0.0001

Data Index: 656129 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7288. Min Act: -0.0001

Data Index: 1043421 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7205. Min Act: -0.0001

Data Index: 528319 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.6730. Min Act: -0.0001

Data Index: 823956 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7223. Min Act: -0.0001

Data Index: 1003769 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7024. Min Act: -0.0001

Data Index: 1136625 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.6951. Min Act: -0.0001

Data Index: 1258815 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.6929. Min Act: -0.0001

Data Index: 558975 (C4 (Web Text))

Max Activating Token Index: 411