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

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

Neuron 757 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: 4.1651. Min Range: -4.1651

Max Act: 4.1651. Min Act: -0.1700

Data Index: 963358 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 4.1651. Min Range: -4.1651

Max Act: 4.0025. Min Act: -0.1700

Data Index: 1206649 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.9862. Min Act: -0.1700

Data Index: 743320 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.9677. Min Act: -0.1700

Data Index: 535574 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.9490. Min Act: -0.1700

Data Index: 1217739 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.9268. Min Act: -0.1700

Data Index: 208751 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.9049. Min Act: -0.1700

Data Index: 1284182 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.8986. Min Act: -0.1700

Data Index: 832176 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.8795. Min Act: -0.1700

Data Index: 684988 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.8725. Min Act: -0.1700

Data Index: 1239646 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.9090. Min Act: -0.1700

Data Index: 856899 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.8828. Min Act: -0.1700

Data Index: 1166022 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.8750. Min Act: -0.1700

Data Index: 624794 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.8970. Min Act: -0.1700

Data Index: 303469 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.8596. Min Act: -0.1700

Data Index: 988256 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.8546. Min Act: -0.1700

Data Index: 1069517 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.8548. Min Act: -0.1700

Data Index: 339497 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.8368. Min Act: -0.1700

Data Index: 639333 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.8592. Min Act: -0.1700

Data Index: 796386 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.8530. Min Act: -0.1700

Data Index: 675464 (C4 (Web Text))

Max Activating Token Index: 243