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

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

Neuron 1204 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8892. Min Range: -3.8892

Max Act: 3.8892. Min Act: -0.1700

Data Index: 1176086 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 3.8892. Min Range: -3.8892

Max Act: 3.8110. Min Act: -0.1700

Data Index: 377489 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 3.8892. Min Range: -3.8892

Max Act: 3.8267. Min Act: -0.1700

Data Index: 1045136 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 3.8892. Min Range: -3.8892

Max Act: 3.8110. Min Act: -0.1700

Data Index: 579215 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 3.8892. Min Range: -3.8892

Max Act: 3.8110. Min Act: -0.1700

Data Index: 737264 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 3.8892. Min Range: -3.8892

Max Act: 3.7954. Min Act: -0.1700

Data Index: 355704 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 3.8892. Min Range: -3.8892

Max Act: 3.8267. Min Act: -0.1700

Data Index: 461044 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 3.8892. Min Range: -3.8892

Max Act: 3.8110. Min Act: -0.1700

Data Index: 128141 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 3.8892. Min Range: -3.8892

Max Act: 3.8110. Min Act: -0.1700

Data Index: 259600 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 3.8892. Min Range: -3.8892

Max Act: 3.7798. Min Act: -0.1700

Data Index: 1101208 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 3.8892. Min Range: -3.8892

Max Act: 3.7954. Min Act: -0.1700

Data Index: 433374 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 3.8892. Min Range: -3.8892

Max Act: 3.7485. Min Act: -0.1700

Data Index: 370478 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 3.8892. Min Range: -3.8892

Max Act: 3.7798. Min Act: -0.1700

Data Index: 677854 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 3.8892. Min Range: -3.8892

Max Act: 3.7798. Min Act: -0.1700

Data Index: 1180070 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 3.8892. Min Range: -3.8892

Max Act: 3.7641. Min Act: -0.1700

Data Index: 245725 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 3.8892. Min Range: -3.8892

Max Act: 3.7328. Min Act: -0.1700

Data Index: 221180 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 3.8892. Min Range: -3.8892

Max Act: 3.7798. Min Act: -0.1700

Data Index: 397656 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 3.8892. Min Range: -3.8892

Max Act: 3.7485. Min Act: -0.1700

Data Index: 11591 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 3.8892. Min Range: -3.8892

Max Act: 3.7641. Min Act: -0.1700

Data Index: 518448 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 3.8892. Min Range: -3.8892

Max Act: 3.7641. Min Act: -0.1700

Data Index: 523948 (C4 (Web Text))

Max Activating Token Index: 918