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

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

Neuron 2678 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: 0.3156. Min Range: -0.3156

Max Act: 0.3156. Min Act: -0.0000

Data Index: 1000416 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.3127. Min Act: -0.0001

Data Index: 256548 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2718. Min Act: -0.0001

Data Index: 119132 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2981. Min Act: -0.0000

Data Index: 116617 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.3034. Min Act: -0.0000

Data Index: 1062412 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2904. Min Act: -0.0001

Data Index: 1024627 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2775. Min Act: -0.0001

Data Index: 675685 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1309371 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2876. Min Act: -0.0001

Data Index: 262106 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2525. Min Act: -0.0001

Data Index: 433292 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2631. Min Act: -0.0001

Data Index: 343555 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2596. Min Act: -0.0000

Data Index: 688315 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2539. Min Act: -0.0001

Data Index: 947610 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2513. Min Act: -0.0001

Data Index: 1046227 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2781. Min Act: -0.0001

Data Index: 314756 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2599. Min Act: -0.0001

Data Index: 337998 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2606. Min Act: -0.0001

Data Index: 677066 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2418. Min Act: -0.0001

Data Index: 51828 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2491. Min Act: -0.0001

Data Index: 253299 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 0.3156. Min Range: -0.3156

Max Act: 0.2647. Min Act: -0.0001

Data Index: 1109012 (C4 (Web Text))

Max Activating Token Index: 972