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

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

Neuron 186 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: 3.5540. Min Range: -3.5540

Max Act: 3.5540. Min Act: -0.1695

Data Index: 272155 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 3.5540. Min Range: -3.5540

Max Act: 3.3579. Min Act: -0.1700

Data Index: 842814 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 3.5540. Min Range: -3.5540

Max Act: 3.3292. Min Act: -0.1700

Data Index: 1358635 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 3.5540. Min Range: -3.5540

Max Act: 3.3158. Min Act: -0.1699

Data Index: 460002 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 3.5540. Min Range: -3.5540

Max Act: 3.3152. Min Act: -0.1675

Data Index: 690565 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 3.5540. Min Range: -3.5540

Max Act: 3.3158. Min Act: -0.1700

Data Index: 508978 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 3.5540. Min Range: -3.5540

Max Act: 3.3088. Min Act: -0.1698

Data Index: 1197631 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 3.5540. Min Range: -3.5540

Max Act: 3.2922. Min Act: -0.1700

Data Index: 552325 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 3.5540. Min Range: -3.5540

Max Act: 3.2970. Min Act: -0.1699

Data Index: 660919 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 3.5540. Min Range: -3.5540

Max Act: 3.3077. Min Act: -0.1700

Data Index: 584325 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 3.5540. Min Range: -3.5540

Max Act: 3.2937. Min Act: -0.1700

Data Index: 693121 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 3.5540. Min Range: -3.5540

Max Act: 3.2792. Min Act: -0.1018

Data Index: 302493 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 3.5540. Min Range: -3.5540

Max Act: 3.2621. Min Act: -0.1700

Data Index: 200158 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 3.5540. Min Range: -3.5540

Max Act: 3.2660. Min Act: -0.1700

Data Index: 872466 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 3.5540. Min Range: -3.5540

Max Act: 3.2546. Min Act: -0.1699

Data Index: 585064 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 3.5540. Min Range: -3.5540

Max Act: 3.2498. Min Act: -0.1700

Data Index: 623437 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 3.5540. Min Range: -3.5540

Max Act: 3.2324. Min Act: -0.1700

Data Index: 10179 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 3.5540. Min Range: -3.5540

Max Act: 3.2511. Min Act: -0.1700

Data Index: 1142847 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 3.5540. Min Range: -3.5540

Max Act: 3.2409. Min Act: -0.1699

Data Index: 235679 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 3.5540. Min Range: -3.5540

Max Act: 3.2460. Min Act: -0.1700

Data Index: 706538 (C4 (Web Text))

Max Activating Token Index: 492