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

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

Neuron 571 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.7186. Min Act: -0.1700

Data Index: 842959 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.6247. Min Act: -0.1700

Data Index: 55966 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.5934. Min Act: -0.1700

Data Index: 210650 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.4994. Min Act: -0.1700

Data Index: 189293 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.5620. Min Act: -0.1700

Data Index: 1307794 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.4994. Min Act: -0.1700

Data Index: 676539 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.5620. Min Act: -0.1700

Data Index: 850536 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.5307. Min Act: -0.1700

Data Index: 1009742 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.4680. Min Act: -0.1700

Data Index: 1220735 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.4680. Min Act: -0.1700

Data Index: 1159405 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.4367. Min Act: -0.1700

Data Index: 238471 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.4994. Min Act: -0.1700

Data Index: 881926 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.4994. Min Act: -0.1700

Data Index: 177833 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.5307. Min Act: -0.1700

Data Index: 399258 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.4994. Min Act: -0.1700

Data Index: 596738 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.4680. Min Act: -0.1700

Data Index: 1244389 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.4367. Min Act: -0.1700

Data Index: 920235 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.4994. Min Act: -0.1700

Data Index: 963203 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.4367. Min Act: -0.1700

Data Index: 398038 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 3.7186. Min Range: -3.7186

Max Act: 3.4053. Min Act: -0.1700

Data Index: 1112841 (C4 (Web Text))

Max Activating Token Index: 872