Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 550 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.4247. Min Act: -0.1700

Data Index: 806816 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.2997. Min Act: -0.1700

Data Index: 1355680 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.2685. Min Act: -0.1700

Data Index: 553559 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.2372. Min Act: -0.1700

Data Index: 269327 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.2060. Min Act: -0.1700

Data Index: 743617 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.1122. Min Act: -0.1700

Data Index: 762567 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.1747. Min Act: -0.1700

Data Index: 1297623 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.1122. Min Act: -0.1700

Data Index: 1059215 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.1122. Min Act: -0.1700

Data Index: 705515 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.0497. Min Act: -0.1700

Data Index: 652377 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.0497. Min Act: -0.1700

Data Index: 190842 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.0497. Min Act: -0.1700

Data Index: 406299 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 5.4247. Min Range: -5.4247

Max Act: 4.9872. Min Act: -0.1700

Data Index: 758145 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.0497. Min Act: -0.1700

Data Index: 170051 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 5.4247. Min Range: -5.4247

Max Act: 4.9560. Min Act: -0.1700

Data Index: 653163 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.0497. Min Act: -0.1700

Data Index: 6249 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.0497. Min Act: -0.1700

Data Index: 590567 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 5.4247. Min Range: -5.4247

Max Act: 5.0185. Min Act: -0.1700

Data Index: 521936 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 5.4247. Min Range: -5.4247

Max Act: 4.9872. Min Act: -0.1700

Data Index: 52494 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 5.4247. Min Range: -5.4247

Max Act: 4.9872. Min Act: -0.1700

Data Index: 711533 (C4 (Web Text))

Max Activating Token Index: 703