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

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

Neuron 1419 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: 3.6943. Min Range: -3.6943

Max Act: 3.6943. Min Act: -0.1700

Data Index: 758536 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.6943. Min Act: -0.1700

Data Index: 170833 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.4751. Min Act: -0.1700

Data Index: 771874 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.5064. Min Act: -0.1700

Data Index: 1055033 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.4437. Min Act: -0.1700

Data Index: 675306 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.4281. Min Act: -0.1700

Data Index: 1249102 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.4124. Min Act: -0.1700

Data Index: 1189708 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.4437. Min Act: -0.1700

Data Index: 562076 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.3967. Min Act: -0.1700

Data Index: 1089534 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.4594. Min Act: -0.1700

Data Index: 733854 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.3810. Min Act: -0.1700

Data Index: 1313705 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.3967. Min Act: -0.1700

Data Index: 44754 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.4281. Min Act: -0.1700

Data Index: 1255817 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.3967. Min Act: -0.1700

Data Index: 942944 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.3967. Min Act: -0.1700

Data Index: 232274 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.4124. Min Act: -0.1700

Data Index: 1084468 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.3810. Min Act: -0.1700

Data Index: 383551 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.3967. Min Act: -0.1700

Data Index: 1300486 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.3653. Min Act: -0.1700

Data Index: 419121 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.3496. Min Act: -0.1700

Data Index: 298605 (C4 (Web Text))

Max Activating Token Index: 859