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

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

Neuron 1335 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8560. Min Range: -5.8560

Max Act: 5.8560. Min Act: -0.1700

Data Index: 254622 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 5.8560. Min Range: -5.8560

Max Act: 5.7310. Min Act: -0.1700

Data Index: 979306 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 5.8560. Min Range: -5.8560

Max Act: 5.6060. Min Act: -0.1700

Data Index: 278562 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 5.8560. Min Range: -5.8560

Max Act: 5.6372. Min Act: -0.1700

Data Index: 6266 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 5.8560. Min Range: -5.8560

Max Act: 5.6372. Min Act: -0.1700

Data Index: 988678 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 5.8560. Min Range: -5.8560

Max Act: 5.5747. Min Act: -0.1700

Data Index: 1177448 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 5.8560. Min Range: -5.8560

Max Act: 5.5122. Min Act: -0.1700

Data Index: 902421 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 5.8560. Min Range: -5.8560

Max Act: 5.5122. Min Act: -0.1700

Data Index: 749282 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 5.8560. Min Range: -5.8560

Max Act: 5.5435. Min Act: -0.1700

Data Index: 771253 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 5.8560. Min Range: -5.8560

Max Act: 5.4810. Min Act: -0.1700

Data Index: 404458 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 5.8560. Min Range: -5.8560

Max Act: 5.5435. Min Act: -0.1700

Data Index: 825433 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 5.8560. Min Range: -5.8560

Max Act: 5.5122. Min Act: -0.1700

Data Index: 1354494 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 5.8560. Min Range: -5.8560

Max Act: 5.4810. Min Act: -0.1700

Data Index: 1304683 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 5.8560. Min Range: -5.8560

Max Act: 5.5122. Min Act: -0.1700

Data Index: 877768 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 5.8560. Min Range: -5.8560

Max Act: 5.4810. Min Act: -0.1700

Data Index: 1054749 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 5.8560. Min Range: -5.8560

Max Act: 5.4185. Min Act: -0.1700

Data Index: 769682 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 5.8560. Min Range: -5.8560

Max Act: 5.4810. Min Act: -0.1700

Data Index: 523742 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 5.8560. Min Range: -5.8560

Max Act: 5.4497. Min Act: -0.1700

Data Index: 1060405 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 5.8560. Min Range: -5.8560

Max Act: 5.4810. Min Act: -0.1700

Data Index: 907618 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 5.8560. Min Range: -5.8560

Max Act: 5.4185. Min Act: -0.1700

Data Index: 85620 (C4 (Web Text))

Max Activating Token Index: 559