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

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

Neuron 1786 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: 3.6360. Min Range: -3.6360

Max Act: 3.6360. Min Act: -0.1700

Data Index: 904357 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 3.6360. Min Range: -3.6360

Max Act: 3.6047. Min Act: -0.1700

Data Index: 502805 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 3.6360. Min Range: -3.6360

Max Act: 3.5420. Min Act: -0.1700

Data Index: 450178 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 3.6360. Min Range: -3.6360

Max Act: 3.5420. Min Act: -0.1700

Data Index: 1084086 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 3.6360. Min Range: -3.6360

Max Act: 3.4794. Min Act: -0.1700

Data Index: 1220403 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 3.6360. Min Range: -3.6360

Max Act: 3.4794. Min Act: -0.1700

Data Index: 839190 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 3.6360. Min Range: -3.6360

Max Act: 3.4794. Min Act: -0.1700

Data Index: 551672 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 3.6360. Min Range: -3.6360

Max Act: 3.4480. Min Act: -0.1700

Data Index: 545211 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 3.6360. Min Range: -3.6360

Max Act: 3.4480. Min Act: -0.1700

Data Index: 1060125 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 3.6360. Min Range: -3.6360

Max Act: 3.4794. Min Act: -0.1700

Data Index: 1303219 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 3.6360. Min Range: -3.6360

Max Act: 3.4167. Min Act: -0.1700

Data Index: 32787 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 3.6360. Min Range: -3.6360

Max Act: 3.4167. Min Act: -0.1700

Data Index: 688735 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 3.6360. Min Range: -3.6360

Max Act: 3.4480. Min Act: -0.1700

Data Index: 878105 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 3.6360. Min Range: -3.6360

Max Act: 3.4480. Min Act: -0.1700

Data Index: 956571 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 3.6360. Min Range: -3.6360

Max Act: 3.4480. Min Act: -0.1700

Data Index: 631704 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 3.6360. Min Range: -3.6360

Max Act: 3.4167. Min Act: -0.1700

Data Index: 648510 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 3.6360. Min Range: -3.6360

Max Act: 3.4167. Min Act: -0.1700

Data Index: 608091 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 3.6360. Min Range: -3.6360

Max Act: 3.4167. Min Act: -0.1700

Data Index: 944006 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 3.6360. Min Range: -3.6360

Max Act: 3.4167. Min Act: -0.1700

Data Index: 156380 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 3.6360. Min Range: -3.6360

Max Act: 3.4480. Min Act: -0.1700

Data Index: 677375 (C4 (Web Text))

Max Activating Token Index: 393