Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1025 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9166. Min Range: -3.9166

Max Act: 3.9166. Min Act: -0.1700

Data Index: 265262 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 3.9166. Min Range: -3.9166

Max Act: 3.7602. Min Act: -0.1700

Data Index: 862966 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 3.9166. Min Range: -3.9166

Max Act: 3.7602. Min Act: -0.1700

Data Index: 742221 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 3.9166. Min Range: -3.9166

Max Act: 3.7289. Min Act: -0.1700

Data Index: 40551 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 3.9166. Min Range: -3.9166

Max Act: 3.7289. Min Act: -0.1700

Data Index: 1294750 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 3.9166. Min Range: -3.9166

Max Act: 3.6663. Min Act: -0.1700

Data Index: 537437 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 3.9166. Min Range: -3.9166

Max Act: 3.6350. Min Act: -0.1700

Data Index: 322018 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 3.9166. Min Range: -3.9166

Max Act: 3.6663. Min Act: -0.1700

Data Index: 147768 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 3.9166. Min Range: -3.9166

Max Act: 3.6037. Min Act: -0.1700

Data Index: 705207 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 3.9166. Min Range: -3.9166

Max Act: 3.5410. Min Act: -0.1700

Data Index: 1296994 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 3.9166. Min Range: -3.9166

Max Act: 3.5410. Min Act: -0.1700

Data Index: 822972 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 3.9166. Min Range: -3.9166

Max Act: 3.5410. Min Act: -0.1700

Data Index: 1246971 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 3.9166. Min Range: -3.9166

Max Act: 3.5723. Min Act: -0.1700

Data Index: 1223623 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 3.9166. Min Range: -3.9166

Max Act: 3.4940. Min Act: -0.1700

Data Index: 884284 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 3.9166. Min Range: -3.9166

Max Act: 3.4940. Min Act: -0.1700

Data Index: 339600 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 3.9166. Min Range: -3.9166

Max Act: 3.4940. Min Act: -0.1700

Data Index: 1329227 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 3.9166. Min Range: -3.9166

Max Act: 3.5097. Min Act: -0.1700

Data Index: 951317 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 3.9166. Min Range: -3.9166

Max Act: 3.5097. Min Act: -0.1700

Data Index: 432328 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 3.9166. Min Range: -3.9166

Max Act: 3.4627. Min Act: -0.1700

Data Index: 808560 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 3.9166. Min Range: -3.9166

Max Act: 3.4940. Min Act: -0.1700

Data Index: 882158 (C4 (Web Text))

Max Activating Token Index: 170