Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2987 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.0117. Min Range: -3.0117

Max Act: 3.0117. Min Act: -0.1700

Data Index: 1710396 (Open Web Text)

Max Activating Token Index: 592

Text #1

Max Range: 3.0117. Min Range: -3.0117

Max Act: 2.9449. Min Act: -0.1700

Data Index: 1600858 (Open Web Text)

Max Activating Token Index: 838

Text #2

Max Range: 3.0117. Min Range: -3.0117

Max Act: 2.8533. Min Act: -0.1700

Data Index: 7392375 (Open Web Text)

Max Activating Token Index: 409

Text #3

Max Range: 3.0117. Min Range: -3.0117

Max Act: 2.8022. Min Act: -0.1700

Data Index: 5029328 (Open Web Text)

Max Activating Token Index: 665

Text #4

Max Range: 3.0117. Min Range: -3.0117

Max Act: 2.7826. Min Act: -0.1700

Data Index: 3159622 (Open Web Text)

Max Activating Token Index: 386

Text #5

Max Range: 3.0117. Min Range: -3.0117

Max Act: 2.7658. Min Act: -0.1700

Data Index: 4427236 (Open Web Text)

Max Activating Token Index: 126

Text #6

Max Range: 3.0117. Min Range: -3.0117

Max Act: 2.7160. Min Act: -0.1700

Data Index: 3421137 (Open Web Text)

Max Activating Token Index: 465

Text #7

Max Range: 3.0117. Min Range: -3.0117

Max Act: 2.7317. Min Act: -0.1700

Data Index: 2716579 (Open Web Text)

Max Activating Token Index: 656

Text #8

Max Range: 3.0117. Min Range: -3.0117

Max Act: 2.7149. Min Act: -0.1700

Data Index: 1980699 (Open Web Text)

Max Activating Token Index: 927

Text #9

Max Range: 3.0117. Min Range: -3.0117

Max Act: 2.7005. Min Act: -0.1700

Data Index: 572511 (Open Web Text)

Max Activating Token Index: 591

Text #10

Max Range: 3.0117. Min Range: -3.0117

Max Act: 2.6857. Min Act: -0.1700

Data Index: 8320308 (Open Web Text)

Max Activating Token Index: 714

Text #11

Max Range: 3.0117. Min Range: -3.0117

Max Act: 2.7024. Min Act: -0.1700

Data Index: 6149373 (Open Web Text)

Max Activating Token Index: 974

Text #12

Max Range: 3.0117. Min Range: -3.0117

Max Act: 2.6840. Min Act: -0.1700

Data Index: 6953593 (Open Web Text)

Max Activating Token Index: 489

Text #13

Max Range: 3.0117. Min Range: -3.0117

Max Act: 2.6751. Min Act: -0.1700

Data Index: 5152599 (Open Web Text)

Max Activating Token Index: 984

Text #14

Max Range: 3.0117. Min Range: -3.0117

Max Act: 2.6561. Min Act: -0.1700

Data Index: 4417501 (Open Web Text)

Max Activating Token Index: 320

Text #15

Max Range: 3.0117. Min Range: -3.0117

Max Act: 2.6665. Min Act: -0.1700

Data Index: 8395386 (Open Web Text)

Max Activating Token Index: 761

Text #16

Max Range: 3.0117. Min Range: -3.0117

Max Act: 2.6515. Min Act: -0.1700

Data Index: 5772030 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.0117. Min Range: -3.0117

Max Act: 2.6558. Min Act: -0.1700

Data Index: 1287826 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.0117. Min Range: -3.0117

Max Act: 2.6281. Min Act: -0.1700

Data Index: 4498259 (Open Web Text)

Max Activating Token Index: 769

Text #19

Max Range: 3.0117. Min Range: -3.0117

Max Act: 2.6226. Min Act: -0.1700

Data Index: 1270338 (Open Web Text)

Max Activating Token Index: 711