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

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

Neuron 1189 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.1168. Min Range: -5.1168

Max Act: 5.0855. Min Act: -0.1700

Data Index: 335194 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 5.1168. Min Range: -5.1168

Max Act: 5.0543. Min Act: -0.1700

Data Index: 405445 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 5.1168. Min Range: -5.1168

Max Act: 5.0543. Min Act: -0.1700

Data Index: 394570 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 5.1168. Min Range: -5.1168

Max Act: 5.0543. Min Act: -0.1700

Data Index: 640402 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 5.1168. Min Range: -5.1168

Max Act: 5.1168. Min Act: -0.1700

Data Index: 444002 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 5.1168. Min Range: -5.1168

Max Act: 5.0230. Min Act: -0.1700

Data Index: 182851 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 5.1168. Min Range: -5.1168

Max Act: 5.0543. Min Act: -0.1700

Data Index: 892364 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 5.1168. Min Range: -5.1168

Max Act: 5.0230. Min Act: -0.1700

Data Index: 648815 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 5.1168. Min Range: -5.1168

Max Act: 4.9605. Min Act: -0.1700

Data Index: 810645 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 5.1168. Min Range: -5.1168

Max Act: 4.9605. Min Act: -0.1700

Data Index: 186825 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 5.1168. Min Range: -5.1168

Max Act: 4.9918. Min Act: -0.1700

Data Index: 905643 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 5.1168. Min Range: -5.1168

Max Act: 4.9918. Min Act: -0.1700

Data Index: 587006 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 5.1168. Min Range: -5.1168

Max Act: 4.9293. Min Act: -0.1700

Data Index: 1457111 (Python Code)

Max Activating Token Index: 445

Text #13

Max Range: 5.1168. Min Range: -5.1168

Max Act: 4.9293. Min Act: -0.1700

Data Index: 98375 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 5.1168. Min Range: -5.1168

Max Act: 4.8980. Min Act: -0.1700

Data Index: 379779 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 5.1168. Min Range: -5.1168

Max Act: 4.8980. Min Act: -0.1700

Data Index: 1229091 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 5.1168. Min Range: -5.1168

Max Act: 4.8980. Min Act: -0.1700

Data Index: 28708 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 5.1168. Min Range: -5.1168

Max Act: 4.8355. Min Act: -0.1700

Data Index: 46669 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 5.1168. Min Range: -5.1168

Max Act: 4.8668. Min Act: -0.1700

Data Index: 246588 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 5.1168. Min Range: -5.1168

Max Act: 4.8668. Min Act: -0.1700

Data Index: 442506 (C4 (Web Text))

Max Activating Token Index: 793