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

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

Neuron 468 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: 5.7091. Min Range: -5.7091

Max Act: 5.7091. Min Act: -0.1700

Data Index: 985979 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 5.7091. Min Range: -5.7091

Max Act: 5.6466. Min Act: -0.1700

Data Index: 895636 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 5.7091. Min Range: -5.7091

Max Act: 5.6466. Min Act: -0.1700

Data Index: 319341 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 5.7091. Min Range: -5.7091

Max Act: 5.6154. Min Act: -0.1700

Data Index: 128852 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 5.7091. Min Range: -5.7091

Max Act: 5.6154. Min Act: -0.1700

Data Index: 476078 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 5.7091. Min Range: -5.7091

Max Act: 5.5529. Min Act: -0.1700

Data Index: 751008 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 5.7091. Min Range: -5.7091

Max Act: 5.5841. Min Act: -0.1700

Data Index: 603342 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 5.7091. Min Range: -5.7091

Max Act: 5.5529. Min Act: -0.1700

Data Index: 87815 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 5.7091. Min Range: -5.7091

Max Act: 5.5529. Min Act: -0.1700

Data Index: 591533 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 5.7091. Min Range: -5.7091

Max Act: 5.5529. Min Act: -0.1700

Data Index: 1156324 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 5.7091. Min Range: -5.7091

Max Act: 5.5216. Min Act: -0.1700

Data Index: 809749 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 5.7091. Min Range: -5.7091

Max Act: 5.5216. Min Act: -0.1700

Data Index: 1167758 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 5.7091. Min Range: -5.7091

Max Act: 5.4904. Min Act: -0.1700

Data Index: 912649 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 5.7091. Min Range: -5.7091

Max Act: 5.5216. Min Act: -0.1700

Data Index: 422852 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 5.7091. Min Range: -5.7091

Max Act: 5.4591. Min Act: -0.1700

Data Index: 659734 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 5.7091. Min Range: -5.7091

Max Act: 5.4591. Min Act: -0.1700

Data Index: 102086 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 5.7091. Min Range: -5.7091

Max Act: 5.4591. Min Act: -0.1700

Data Index: 476219 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 5.7091. Min Range: -5.7091

Max Act: 5.4591. Min Act: -0.1700

Data Index: 662935 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 5.7091. Min Range: -5.7091

Max Act: 5.4591. Min Act: -0.1700

Data Index: 1056989 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 5.7091. Min Range: -5.7091

Max Act: 5.4904. Min Act: -0.1700

Data Index: 734809 (C4 (Web Text))

Max Activating Token Index: 828