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

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

Neuron 824 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7025. Min Range: -5.7025

Max Act: 5.6713. Min Act: -0.1700

Data Index: 105749 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 5.7025. Min Range: -5.7025

Max Act: 5.7025. Min Act: -0.1700

Data Index: 232014 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 5.7025. Min Range: -5.7025

Max Act: 5.6088. Min Act: -0.1700

Data Index: 448513 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 5.7025. Min Range: -5.7025

Max Act: 5.6088. Min Act: -0.1700

Data Index: 98003 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 5.7025. Min Range: -5.7025

Max Act: 5.5463. Min Act: -0.1700

Data Index: 225680 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 5.7025. Min Range: -5.7025

Max Act: 5.4838. Min Act: -0.1700

Data Index: 1145654 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 5.7025. Min Range: -5.7025

Max Act: 5.4525. Min Act: -0.1700

Data Index: 395885 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 5.7025. Min Range: -5.7025

Max Act: 5.4213. Min Act: -0.1700

Data Index: 661067 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 5.7025. Min Range: -5.7025

Max Act: 5.5150. Min Act: -0.1700

Data Index: 776564 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 5.7025. Min Range: -5.7025

Max Act: 5.3275. Min Act: -0.1700

Data Index: 1219814 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 5.7025. Min Range: -5.7025

Max Act: 5.4213. Min Act: -0.1700

Data Index: 1302618 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 5.7025. Min Range: -5.7025

Max Act: 5.2963. Min Act: -0.1700

Data Index: 302930 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 5.7025. Min Range: -5.7025

Max Act: 5.3900. Min Act: -0.1700

Data Index: 361090 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 5.7025. Min Range: -5.7025

Max Act: 5.3275. Min Act: -0.1700

Data Index: 590240 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 5.7025. Min Range: -5.7025

Max Act: 5.2650. Min Act: -0.1700

Data Index: 577362 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 5.7025. Min Range: -5.7025

Max Act: 5.2025. Min Act: -0.1700

Data Index: 550284 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 5.7025. Min Range: -5.7025

Max Act: 5.1088. Min Act: -0.1700

Data Index: 1348660 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 5.7025. Min Range: -5.7025

Max Act: 5.2338. Min Act: -0.1700

Data Index: 114152 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 5.7025. Min Range: -5.7025

Max Act: 5.1400. Min Act: -0.1700

Data Index: 1326428 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 5.7025. Min Range: -5.7025

Max Act: 5.1713. Min Act: -0.1700

Data Index: 751488 (C4 (Web Text))

Max Activating Token Index: 729