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

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

Neuron 184 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7143. Min Range: -5.7143

Max Act: 5.7143. Min Act: -0.1700

Data Index: 1133329 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 5.7143. Min Range: -5.7143

Max Act: 5.6205. Min Act: -0.1700

Data Index: 702756 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 5.7143. Min Range: -5.7143

Max Act: 5.6205. Min Act: -0.1700

Data Index: 1187817 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 5.7143. Min Range: -5.7143

Max Act: 5.5268. Min Act: -0.1700

Data Index: 248324 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 5.7143. Min Range: -5.7143

Max Act: 5.4330. Min Act: -0.1700

Data Index: 912580 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 5.7143. Min Range: -5.7143

Max Act: 5.4643. Min Act: -0.1700

Data Index: 775794 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 5.7143. Min Range: -5.7143

Max Act: 5.4643. Min Act: -0.1700

Data Index: 308225 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 5.7143. Min Range: -5.7143

Max Act: 5.4955. Min Act: -0.1700

Data Index: 796102 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 5.7143. Min Range: -5.7143

Max Act: 5.4955. Min Act: -0.1700

Data Index: 1090458 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 5.7143. Min Range: -5.7143

Max Act: 5.4018. Min Act: -0.1700

Data Index: 985971 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 5.7143. Min Range: -5.7143

Max Act: 5.4018. Min Act: -0.1700

Data Index: 630843 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 5.7143. Min Range: -5.7143

Max Act: 5.2455. Min Act: -0.1700

Data Index: 443232 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 5.7143. Min Range: -5.7143

Max Act: 5.2768. Min Act: -0.1700

Data Index: 158445 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 5.7143. Min Range: -5.7143

Max Act: 5.2768. Min Act: -0.1700

Data Index: 1127538 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 5.7143. Min Range: -5.7143

Max Act: 5.2143. Min Act: -0.1700

Data Index: 956841 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 5.7143. Min Range: -5.7143

Max Act: 5.2143. Min Act: -0.1700

Data Index: 733973 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 5.7143. Min Range: -5.7143

Max Act: 5.2455. Min Act: -0.1700

Data Index: 407174 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 5.7143. Min Range: -5.7143

Max Act: 5.2455. Min Act: -0.1700

Data Index: 492214 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 5.7143. Min Range: -5.7143

Max Act: 5.2143. Min Act: -0.1700

Data Index: 285207 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 5.7143. Min Range: -5.7143

Max Act: 5.1830. Min Act: -0.1700

Data Index: 762052 (C4 (Web Text))

Max Activating Token Index: 457