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

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

Neuron 1084 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: 5.4601. Min Range: -5.4601

Max Act: 5.4601. Min Act: -0.1700

Data Index: 1220699 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 5.4601. Min Range: -5.4601

Max Act: 5.3507. Min Act: -0.1700

Data Index: 1317332 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 5.4601. Min Range: -5.4601

Max Act: 5.3507. Min Act: -0.1700

Data Index: 819559 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 5.4601. Min Range: -5.4601

Max Act: 5.3038. Min Act: -0.1700

Data Index: 391595 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 5.4601. Min Range: -5.4601

Max Act: 5.3351. Min Act: -0.1700

Data Index: 859929 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 5.4601. Min Range: -5.4601

Max Act: 5.1319. Min Act: -0.1700

Data Index: 532797 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 5.4601. Min Range: -5.4601

Max Act: 5.1632. Min Act: -0.1700

Data Index: 269365 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 5.4601. Min Range: -5.4601

Max Act: 5.1476. Min Act: -0.1700

Data Index: 1014080 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 5.4601. Min Range: -5.4601

Max Act: 5.1163. Min Act: -0.1700

Data Index: 597292 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 5.4601. Min Range: -5.4601

Max Act: 5.1163. Min Act: -0.1700

Data Index: 227110 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 5.4601. Min Range: -5.4601

Max Act: 5.0694. Min Act: -0.1700

Data Index: 1254597 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 5.4601. Min Range: -5.4601

Max Act: 5.1007. Min Act: -0.1700

Data Index: 1244942 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 5.4601. Min Range: -5.4601

Max Act: 5.1007. Min Act: -0.1700

Data Index: 846015 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 5.4601. Min Range: -5.4601

Max Act: 5.1007. Min Act: -0.1700

Data Index: 688684 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 5.4601. Min Range: -5.4601

Max Act: 5.1319. Min Act: -0.1700

Data Index: 1229700 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 5.4601. Min Range: -5.4601

Max Act: 5.1007. Min Act: -0.1700

Data Index: 1319158 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 5.4601. Min Range: -5.4601

Max Act: 5.0382. Min Act: -0.1700

Data Index: 1049484 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 5.4601. Min Range: -5.4601

Max Act: 4.9913. Min Act: -0.1700

Data Index: 1211861 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 5.4601. Min Range: -5.4601

Max Act: 5.0382. Min Act: -0.1700

Data Index: 1247055 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 5.4601. Min Range: -5.4601

Max Act: 5.0226. Min Act: -0.1700

Data Index: 54361 (C4 (Web Text))

Max Activating Token Index: 148