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

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

Neuron 446 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: 8.6197. Min Range: -8.6197

Max Act: 8.6197. Min Act: -0.1700

Data Index: 838945 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 8.6197. Min Range: -8.6197

Max Act: 8.4322. Min Act: -0.1700

Data Index: 475834 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 8.6197. Min Range: -8.6197

Max Act: 8.4322. Min Act: -0.1700

Data Index: 437238 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 8.6197. Min Range: -8.6197

Max Act: 8.3385. Min Act: -0.1700

Data Index: 425989 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 8.6197. Min Range: -8.6197

Max Act: 8.2447. Min Act: -0.1700

Data Index: 341281 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 8.6197. Min Range: -8.6197

Max Act: 8.2760. Min Act: -0.1700

Data Index: 605826 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 8.6197. Min Range: -8.6197

Max Act: 8.2760. Min Act: -0.1700

Data Index: 910800 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 8.6197. Min Range: -8.6197

Max Act: 8.2760. Min Act: -0.1700

Data Index: 1105429 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 8.6197. Min Range: -8.6197

Max Act: 8.2135. Min Act: -0.1700

Data Index: 1075182 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 8.6197. Min Range: -8.6197

Max Act: 8.1822. Min Act: -0.1700

Data Index: 1106924 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 8.6197. Min Range: -8.6197

Max Act: 8.1822. Min Act: -0.1700

Data Index: 1359340 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 8.6197. Min Range: -8.6197

Max Act: 8.1510. Min Act: -0.1700

Data Index: 614135 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 8.6197. Min Range: -8.6197

Max Act: 8.1822. Min Act: -0.1700

Data Index: 1114616 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 8.6197. Min Range: -8.6197

Max Act: 8.1197. Min Act: -0.1700

Data Index: 871200 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 8.6197. Min Range: -8.6197

Max Act: 8.0260. Min Act: -0.1700

Data Index: 1131291 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 8.6197. Min Range: -8.6197

Max Act: 8.0572. Min Act: -0.1700

Data Index: 1284570 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 8.6197. Min Range: -8.6197

Max Act: 8.0572. Min Act: -0.1700

Data Index: 76959 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 8.6197. Min Range: -8.6197

Max Act: 8.1510. Min Act: -0.1700

Data Index: 1148166 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 8.6197. Min Range: -8.6197

Max Act: 8.0260. Min Act: -0.1700

Data Index: 341080 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 8.6197. Min Range: -8.6197

Max Act: 8.0260. Min Act: -0.1700

Data Index: 441353 (C4 (Web Text))

Max Activating Token Index: 853