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

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

Neuron 424 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: 6.2259. Min Range: -6.2259

Max Act: 6.2259. Min Act: -0.1700

Data Index: 265979 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 6.2259. Min Range: -6.2259

Max Act: 6.2178. Min Act: -0.1700

Data Index: 415349 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 6.2259. Min Range: -6.2259

Max Act: 6.1338. Min Act: -0.1700

Data Index: 1030526 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 6.2259. Min Range: -6.2259

Max Act: 6.1159. Min Act: -0.1700

Data Index: 1029945 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 6.2259. Min Range: -6.2259

Max Act: 6.0806. Min Act: -0.1700

Data Index: 1238107 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 6.2259. Min Range: -6.2259

Max Act: 6.0522. Min Act: -0.1700

Data Index: 371692 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 6.2259. Min Range: -6.2259

Max Act: 6.0421. Min Act: -0.1700

Data Index: 1253562 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 6.2259. Min Range: -6.2259

Max Act: 6.0691. Min Act: -0.1700

Data Index: 585980 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 6.2259. Min Range: -6.2259

Max Act: 6.0307. Min Act: -0.1700

Data Index: 1177090 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 6.2259. Min Range: -6.2259

Max Act: 6.0084. Min Act: -0.1700

Data Index: 416407 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 6.2259. Min Range: -6.2259

Max Act: 5.9870. Min Act: -0.1700

Data Index: 369829 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 6.2259. Min Range: -6.2259

Max Act: 5.9640. Min Act: -0.1700

Data Index: 388075 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 6.2259. Min Range: -6.2259

Max Act: 5.9613. Min Act: -0.1700

Data Index: 14435 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 6.2259. Min Range: -6.2259

Max Act: 5.9598. Min Act: -0.1700

Data Index: 485378 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 6.2259. Min Range: -6.2259

Max Act: 5.9559. Min Act: -0.1700

Data Index: 737079 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 6.2259. Min Range: -6.2259

Max Act: 5.9474. Min Act: -0.1700

Data Index: 628926 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 6.2259. Min Range: -6.2259

Max Act: 5.9466. Min Act: -0.1700

Data Index: 1025517 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 6.2259. Min Range: -6.2259

Max Act: 5.9642. Min Act: -0.1700

Data Index: 906180 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 6.2259. Min Range: -6.2259

Max Act: 5.9600. Min Act: -0.1700

Data Index: 496630 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 6.2259. Min Range: -6.2259

Max Act: 5.9423. Min Act: -0.1700

Data Index: 348291 (C4 (Web Text))

Max Activating Token Index: 949