Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 819 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2482. Min Range: -1.2482

Max Act: 1.2482. Min Act: -0.0000

Data Index: 284829 (The Pile)

Max Activating Token Index: 916

Text #1

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.9438. Min Act: -0.0000

Data Index: 1875489 (The Pile)

Max Activating Token Index: 144

Text #2

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.8814. Min Act: -0.0000

Data Index: 1000178 (The Pile)

Max Activating Token Index: 186

Text #3

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.8831. Min Act: -0.0000

Data Index: 693007 (The Pile)

Max Activating Token Index: 524

Text #4

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.8457. Min Act: -0.0000

Data Index: 986759 (The Pile)

Max Activating Token Index: 856

Text #5

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1339840 (The Pile)

Max Activating Token Index: 334

Text #6

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.8596. Min Act: -0.0000

Data Index: 502656 (The Pile)

Max Activating Token Index: 114

Text #7

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.7962. Min Act: -0.0000

Data Index: 1569405 (The Pile)

Max Activating Token Index: 293

Text #8

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.7771. Min Act: -0.0000

Data Index: 1305479 (The Pile)

Max Activating Token Index: 215

Text #9

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.7721. Min Act: -0.0000

Data Index: 203791 (The Pile)

Max Activating Token Index: 130

Text #10

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1103339 (The Pile)

Max Activating Token Index: 51

Text #11

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.7568. Min Act: -0.0000

Data Index: 87555 (The Pile)

Max Activating Token Index: 907

Text #12

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.6698. Min Act: -0.0000

Data Index: 185649 (The Pile)

Max Activating Token Index: 170

Text #13

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.7511. Min Act: -0.0000

Data Index: 1251302 (The Pile)

Max Activating Token Index: 703

Text #14

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.6901. Min Act: -0.0000

Data Index: 709951 (The Pile)

Max Activating Token Index: 275

Text #15

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1112661 (The Pile)

Max Activating Token Index: 552

Text #16

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.6337. Min Act: -0.0000

Data Index: 133442 (The Pile)

Max Activating Token Index: 957

Text #17

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1648806 (The Pile)

Max Activating Token Index: 41

Text #18

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.6231. Min Act: -0.0000

Data Index: 1556353 (The Pile)

Max Activating Token Index: 798

Text #19

Max Range: 1.2482. Min Range: -1.2482

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1081481 (The Pile)

Max Activating Token Index: 38