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

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

Neuron 586 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: 9.7866. Min Range: -9.7866

Max Act: 9.7866. Min Act: -0.1699

Data Index: 198050 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 9.7866. Min Range: -9.7866

Max Act: 9.7414. Min Act: -0.1610

Data Index: 1101965 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 9.7866. Min Range: -9.7866

Max Act: 9.5782. Min Act: -0.1700

Data Index: 30488 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 9.7866. Min Range: -9.7866

Max Act: 9.5538. Min Act: -0.1670

Data Index: 77105 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 9.7866. Min Range: -9.7866

Max Act: 9.5889. Min Act: -0.1700

Data Index: 1281002 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 9.7866. Min Range: -9.7866

Max Act: 9.5891. Min Act: -0.1619

Data Index: 438838 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 9.7866. Min Range: -9.7866

Max Act: 9.4302. Min Act: -0.1691

Data Index: 757799 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 9.7866. Min Range: -9.7866

Max Act: 9.3290. Min Act: -0.1698

Data Index: 1328400 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 9.7866. Min Range: -9.7866

Max Act: 9.3404. Min Act: -0.1695

Data Index: 670233 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 9.7866. Min Range: -9.7866

Max Act: 9.0942. Min Act: -0.1700

Data Index: 383138 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 9.7866. Min Range: -9.7866

Max Act: 9.0056. Min Act: -0.1700

Data Index: 373227 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 9.7866. Min Range: -9.7866

Max Act: 8.9142. Min Act: -0.1700

Data Index: 766450 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 9.7866. Min Range: -9.7866

Max Act: 8.9031. Min Act: -0.1626

Data Index: 1169755 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 9.7866. Min Range: -9.7866

Max Act: 8.8461. Min Act: -0.1700

Data Index: 1217658 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 9.7866. Min Range: -9.7866

Max Act: 8.7836. Min Act: -0.1677

Data Index: 246292 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 9.7866. Min Range: -9.7866

Max Act: 8.7530. Min Act: -0.1642

Data Index: 383381 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 9.7866. Min Range: -9.7866

Max Act: 8.7883. Min Act: -0.1544

Data Index: 1079757 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 9.7866. Min Range: -9.7866

Max Act: 8.7554. Min Act: -0.1593

Data Index: 492755 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 9.7866. Min Range: -9.7866

Max Act: 8.7138. Min Act: -0.1654

Data Index: 998190 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 9.7866. Min Range: -9.7866

Max Act: 8.7166. Min Act: -0.1700

Data Index: 317405 (C4 (Web Text))

Max Activating Token Index: 168