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

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

Neuron 2142 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.3502. Min Act: -0.0001

Data Index: 458293 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.3668. Min Act: -0.0001

Data Index: 106440 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.3133. Min Act: -0.0001

Data Index: 32726 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2968. Min Act: -0.0001

Data Index: 884860 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2850. Min Act: -0.0001

Data Index: 918855 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2871. Min Act: -0.0001

Data Index: 143865 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2855. Min Act: -0.0001

Data Index: 836082 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2818. Min Act: -0.0001

Data Index: 1289878 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2870. Min Act: -0.0001

Data Index: 1284106 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2454. Min Act: -0.0001

Data Index: 7035 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2703. Min Act: -0.0001

Data Index: 40144 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2599. Min Act: -0.0001

Data Index: 24163 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2618. Min Act: -0.0001

Data Index: 449284 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2698. Min Act: -0.0001

Data Index: 971132 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2611. Min Act: -0.0001

Data Index: 21538 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2458. Min Act: -0.0001

Data Index: 939328 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2518. Min Act: -0.0001

Data Index: 730452 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2591. Min Act: -0.0001

Data Index: 980855 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2598. Min Act: -0.0001

Data Index: 343579 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2464. Min Act: -0.0001

Data Index: 225127 (C4 (Web Text))

Max Activating Token Index: 973