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

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

Neuron 770 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: 6.6329. Min Range: -6.6329

Max Act: 6.6329. Min Act: -0.1700

Data Index: 325597 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 6.6329. Min Range: -6.6329

Max Act: 6.1641. Min Act: -0.1700

Data Index: 1158211 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 6.6329. Min Range: -6.6329

Max Act: 6.1329. Min Act: -0.1700

Data Index: 904449 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 6.6329. Min Range: -6.6329

Max Act: 6.1016. Min Act: -0.1700

Data Index: 260407 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 6.6329. Min Range: -6.6329

Max Act: 6.0079. Min Act: -0.1700

Data Index: 1143373 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 6.6329. Min Range: -6.6329

Max Act: 6.0391. Min Act: -0.1700

Data Index: 850853 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 6.6329. Min Range: -6.6329

Max Act: 6.0391. Min Act: -0.1700

Data Index: 243320 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 6.6329. Min Range: -6.6329

Max Act: 5.9141. Min Act: -0.1700

Data Index: 1103226 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 6.6329. Min Range: -6.6329

Max Act: 5.9141. Min Act: -0.1700

Data Index: 1078977 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 6.6329. Min Range: -6.6329

Max Act: 5.9141. Min Act: -0.1700

Data Index: 705762 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 6.6329. Min Range: -6.6329

Max Act: 5.8204. Min Act: -0.1700

Data Index: 1132267 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 6.6329. Min Range: -6.6329

Max Act: 5.8204. Min Act: -0.1700

Data Index: 302963 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 6.6329. Min Range: -6.6329

Max Act: 5.7891. Min Act: -0.1700

Data Index: 919814 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 6.6329. Min Range: -6.6329

Max Act: 5.8204. Min Act: -0.1700

Data Index: 653518 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 6.6329. Min Range: -6.6329

Max Act: 5.6954. Min Act: -0.1700

Data Index: 87281 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 6.6329. Min Range: -6.6329

Max Act: 5.7266. Min Act: -0.1700

Data Index: 326163 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 6.6329. Min Range: -6.6329

Max Act: 5.6954. Min Act: -0.1700

Data Index: 726759 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 6.6329. Min Range: -6.6329

Max Act: 5.6954. Min Act: -0.1700

Data Index: 373422 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 6.6329. Min Range: -6.6329

Max Act: 5.6954. Min Act: -0.1700

Data Index: 316135 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 6.6329. Min Range: -6.6329

Max Act: 5.6329. Min Act: -0.1700

Data Index: 726522 (C4 (Web Text))

Max Activating Token Index: 926