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

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

Neuron 1695 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1293. Min Range: -5.1293

Max Act: 5.1293. Min Act: -0.1700

Data Index: 818956 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 5.1293. Min Range: -5.1293

Max Act: 5.0668. Min Act: -0.1700

Data Index: 419045 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 5.1293. Min Range: -5.1293

Max Act: 5.0356. Min Act: -0.1700

Data Index: 796454 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 5.1293. Min Range: -5.1293

Max Act: 5.0668. Min Act: -0.1700

Data Index: 432302 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 5.1293. Min Range: -5.1293

Max Act: 5.0043. Min Act: -0.1700

Data Index: 684688 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 5.1293. Min Range: -5.1293

Max Act: 5.0043. Min Act: -0.1700

Data Index: 871152 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 5.1293. Min Range: -5.1293

Max Act: 5.0043. Min Act: -0.1700

Data Index: 1313205 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 5.1293. Min Range: -5.1293

Max Act: 4.9731. Min Act: -0.1699

Data Index: 135222 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 5.1293. Min Range: -5.1293

Max Act: 5.0043. Min Act: -0.1700

Data Index: 1196521 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 5.1293. Min Range: -5.1293

Max Act: 5.0043. Min Act: -0.1700

Data Index: 1025836 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 5.1293. Min Range: -5.1293

Max Act: 5.0043. Min Act: -0.1700

Data Index: 491238 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 5.1293. Min Range: -5.1293

Max Act: 4.9731. Min Act: -0.1700

Data Index: 1304794 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 5.1293. Min Range: -5.1293

Max Act: 5.0043. Min Act: -0.1700

Data Index: 849351 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 5.1293. Min Range: -5.1293

Max Act: 4.9731. Min Act: -0.1700

Data Index: 937514 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 5.1293. Min Range: -5.1293

Max Act: 4.9418. Min Act: -0.1700

Data Index: 1287266 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 5.1293. Min Range: -5.1293

Max Act: 4.9418. Min Act: -0.1700

Data Index: 316160 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 5.1293. Min Range: -5.1293

Max Act: 4.9418. Min Act: -0.1700

Data Index: 815494 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 5.1293. Min Range: -5.1293

Max Act: 4.9418. Min Act: -0.1700

Data Index: 373770 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 5.1293. Min Range: -5.1293

Max Act: 4.9418. Min Act: -0.1700

Data Index: 374837 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 5.1293. Min Range: -5.1293

Max Act: 4.9106. Min Act: -0.1700

Data Index: 126500 (C4 (Web Text))

Max Activating Token Index: 881