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

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

Neuron 1684 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: 3.6908. Min Range: -3.6908

Max Act: 3.6908. Min Act: -0.1700

Data Index: 1126683 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5969. Min Act: -0.1700

Data Index: 314202 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5969. Min Act: -0.1700

Data Index: 442219 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5969. Min Act: -0.1700

Data Index: 12981 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5343. Min Act: -0.1700

Data Index: 1142583 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5656. Min Act: -0.1700

Data Index: 435235 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5969. Min Act: -0.1700

Data Index: 488982 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5656. Min Act: -0.1700

Data Index: 706974 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5343. Min Act: -0.1700

Data Index: 440175 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5343. Min Act: -0.1700

Data Index: 1222132 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5343. Min Act: -0.1700

Data Index: 547587 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5029. Min Act: -0.1700

Data Index: 23058 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5343. Min Act: -0.1700

Data Index: 798036 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5343. Min Act: -0.1700

Data Index: 781632 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5343. Min Act: -0.1700

Data Index: 288244 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5029. Min Act: -0.1700

Data Index: 795524 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.4716. Min Act: -0.1700

Data Index: 1097436 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5029. Min Act: -0.1700

Data Index: 440920 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5029. Min Act: -0.1700

Data Index: 275468 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5029. Min Act: -0.1700

Data Index: 702382 (C4 (Web Text))

Max Activating Token Index: 409