Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1913 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8388. Min Range: -3.8388

Max Act: 3.8388. Min Act: -0.1700

Data Index: 1126549 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 3.8388. Min Range: -3.8388

Max Act: 3.7762. Min Act: -0.1700

Data Index: 37500 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 3.8388. Min Range: -3.8388

Max Act: 3.8388. Min Act: -0.1700

Data Index: 1157650 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 3.8388. Min Range: -3.8388

Max Act: 3.8075. Min Act: -0.1700

Data Index: 1006156 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 3.8388. Min Range: -3.8388

Max Act: 3.7450. Min Act: -0.1700

Data Index: 1060449 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 3.8388. Min Range: -3.8388

Max Act: 3.7450. Min Act: -0.1700

Data Index: 1238775 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 3.8388. Min Range: -3.8388

Max Act: 3.8075. Min Act: -0.1700

Data Index: 112624 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 3.8388. Min Range: -3.8388

Max Act: 3.7450. Min Act: -0.1700

Data Index: 500938 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 3.8388. Min Range: -3.8388

Max Act: 3.7450. Min Act: -0.1700

Data Index: 563329 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 3.8388. Min Range: -3.8388

Max Act: 3.7450. Min Act: -0.1700

Data Index: 616671 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 3.8388. Min Range: -3.8388

Max Act: 3.7450. Min Act: -0.1700

Data Index: 297065 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 3.8388. Min Range: -3.8388

Max Act: 3.7137. Min Act: -0.1700

Data Index: 709698 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 3.8388. Min Range: -3.8388

Max Act: 3.7137. Min Act: -0.1700

Data Index: 738237 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 3.8388. Min Range: -3.8388

Max Act: 3.7450. Min Act: -0.1700

Data Index: 1085487 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 3.8388. Min Range: -3.8388

Max Act: 3.7450. Min Act: -0.1700

Data Index: 882595 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 3.8388. Min Range: -3.8388

Max Act: 3.7450. Min Act: -0.1700

Data Index: 891347 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 3.8388. Min Range: -3.8388

Max Act: 3.7450. Min Act: -0.1700

Data Index: 967773 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 3.8388. Min Range: -3.8388

Max Act: 3.7450. Min Act: -0.1700

Data Index: 587460 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 3.8388. Min Range: -3.8388

Max Act: 3.7450. Min Act: -0.1700

Data Index: 260364 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 3.8388. Min Range: -3.8388

Max Act: 3.7450. Min Act: -0.1700

Data Index: 505394 (C4 (Web Text))

Max Activating Token Index: 881