Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 223 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.7380. Min Range: -4.7380

Max Act: 4.7380. Min Act: -0.1700

Data Index: 559583 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 4.7380. Min Range: -4.7380

Max Act: 4.5736. Min Act: -0.1700

Data Index: 496553 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 4.7380. Min Range: -4.7380

Max Act: 4.5570. Min Act: -0.1700

Data Index: 323946 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 4.7380. Min Range: -4.7380

Max Act: 4.5020. Min Act: -0.1700

Data Index: 181093 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 4.7380. Min Range: -4.7380

Max Act: 4.4453. Min Act: -0.1700

Data Index: 1037780 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 4.7380. Min Range: -4.7380

Max Act: 4.4501. Min Act: -0.1700

Data Index: 135630 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 4.7380. Min Range: -4.7380

Max Act: 4.4458. Min Act: -0.1700

Data Index: 367383 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 4.7380. Min Range: -4.7380

Max Act: 4.4911. Min Act: -0.1700

Data Index: 1280144 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 4.7380. Min Range: -4.7380

Max Act: 4.4753. Min Act: -0.1700

Data Index: 95445 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 4.7380. Min Range: -4.7380

Max Act: 4.4788. Min Act: -0.1699

Data Index: 843497 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 4.7380. Min Range: -4.7380

Max Act: 4.4615. Min Act: -0.1700

Data Index: 410876 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 4.7380. Min Range: -4.7380

Max Act: 4.4236. Min Act: -0.1700

Data Index: 1293740 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 4.7380. Min Range: -4.7380

Max Act: 4.4332. Min Act: -0.1700

Data Index: 248396 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 4.7380. Min Range: -4.7380

Max Act: 4.3928. Min Act: -0.1700

Data Index: 1135767 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 4.7380. Min Range: -4.7380

Max Act: 4.3810. Min Act: -0.1700

Data Index: 659527 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 4.7380. Min Range: -4.7380

Max Act: 4.3330. Min Act: -0.1700

Data Index: 1103780 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 4.7380. Min Range: -4.7380

Max Act: 4.3391. Min Act: -0.1700

Data Index: 256971 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 4.7380. Min Range: -4.7380

Max Act: 4.3506. Min Act: -0.1700

Data Index: 1146049 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 4.7380. Min Range: -4.7380

Max Act: 4.3517. Min Act: -0.1700

Data Index: 592855 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 4.7380. Min Range: -4.7380

Max Act: 4.3160. Min Act: -0.1700

Data Index: 1074722 (C4 (Web Text))

Max Activating Token Index: 656