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

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

Neuron 1725 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: 3.9856. Min Range: -3.9856

Max Act: 3.9856. Min Act: -0.1700

Data Index: 1203248 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.8918. Min Act: -0.1700

Data Index: 885025 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.7041. Min Act: -0.1700

Data Index: 1221083 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.7980. Min Act: -0.1700

Data Index: 83774 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.7041. Min Act: -0.1700

Data Index: 675412 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.5789. Min Act: -0.1700

Data Index: 743591 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.6572. Min Act: -0.1700

Data Index: 1041598 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.7041. Min Act: -0.1700

Data Index: 120553 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.6572. Min Act: -0.1700

Data Index: 725328 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.6415. Min Act: -0.1700

Data Index: 350984 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.5789. Min Act: -0.1700

Data Index: 1328262 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.6415. Min Act: -0.1700

Data Index: 766898 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.5632. Min Act: -0.1700

Data Index: 359786 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.5789. Min Act: -0.1700

Data Index: 1307799 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.5946. Min Act: -0.1700

Data Index: 368678 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.6259. Min Act: -0.1700

Data Index: 336823 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.5789. Min Act: -0.1700

Data Index: 47909 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.5789. Min Act: -0.1700

Data Index: 823193 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.5163. Min Act: -0.1700

Data Index: 132320 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.5476. Min Act: -0.1700

Data Index: 1274290 (C4 (Web Text))

Max Activating Token Index: 309