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

Dataset: Open Web Text

Neuron 1372 in Layer 6

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: 4.0952. Min Range: -4.0952

Max Act: 4.0952. Min Act: -0.1700

Data Index: 404751 (Open Web Text)

Max Activating Token Index: 672

Text #1

Max Range: 4.0952. Min Range: -4.0952

Max Act: 4.0835. Min Act: -0.1700

Data Index: 180153 (Open Web Text)

Max Activating Token Index: 348

Text #2

Max Range: 4.0952. Min Range: -4.0952

Max Act: 4.0010. Min Act: -0.1700

Data Index: 4683015 (Open Web Text)

Max Activating Token Index: 616

Text #3

Max Range: 4.0952. Min Range: -4.0952

Max Act: 3.9699. Min Act: -0.1700

Data Index: 1288121 (Open Web Text)

Max Activating Token Index: 927

Text #4

Max Range: 4.0952. Min Range: -4.0952

Max Act: 3.9775. Min Act: -0.1700

Data Index: 8361368 (Open Web Text)

Max Activating Token Index: 533

Text #5

Max Range: 4.0952. Min Range: -4.0952

Max Act: 3.9765. Min Act: -0.1700

Data Index: 7340109 (Open Web Text)

Max Activating Token Index: 233

Text #6

Max Range: 4.0952. Min Range: -4.0952

Max Act: 3.9016. Min Act: -0.1700

Data Index: 5749087 (Open Web Text)

Max Activating Token Index: 829

Text #7

Max Range: 4.0952. Min Range: -4.0952

Max Act: 3.8976. Min Act: -0.1700

Data Index: 8241253 (Open Web Text)

Max Activating Token Index: 361

Text #8

Max Range: 4.0952. Min Range: -4.0952

Max Act: 3.9150. Min Act: -0.1700

Data Index: 1340762 (Open Web Text)

Max Activating Token Index: 674

Text #9

Max Range: 4.0952. Min Range: -4.0952

Max Act: 3.8513. Min Act: -0.1700

Data Index: 4915302 (Open Web Text)

Max Activating Token Index: 91

Text #10

Max Range: 4.0952. Min Range: -4.0952

Max Act: 3.8566. Min Act: -0.1700

Data Index: 5749096 (Open Web Text)

Max Activating Token Index: 249

Text #11

Max Range: 4.0952. Min Range: -4.0952

Max Act: 3.8630. Min Act: -0.1700

Data Index: 713437 (Open Web Text)

Max Activating Token Index: 472

Text #12

Max Range: 4.0952. Min Range: -4.0952

Max Act: 3.8636. Min Act: -0.1700

Data Index: 7260310 (Open Web Text)

Max Activating Token Index: 608

Text #13

Max Range: 4.0952. Min Range: -4.0952

Max Act: 3.8646. Min Act: -0.1700

Data Index: 4643830 (Open Web Text)

Max Activating Token Index: 576

Text #14

Max Range: 4.0952. Min Range: -4.0952

Max Act: 3.8336. Min Act: -0.1700

Data Index: 8197907 (Open Web Text)

Max Activating Token Index: 762

Text #15

Max Range: 4.0952. Min Range: -4.0952

Max Act: 3.8370. Min Act: -0.1700

Data Index: 678102 (Open Web Text)

Max Activating Token Index: 349

Text #16

Max Range: 4.0952. Min Range: -4.0952

Max Act: 3.8370. Min Act: -0.1700

Data Index: 1647639 (Open Web Text)

Max Activating Token Index: 912

Text #17

Max Range: 4.0952. Min Range: -4.0952

Max Act: 3.8117. Min Act: -0.1700

Data Index: 1495099 (Open Web Text)

Max Activating Token Index: 767

Text #18

Max Range: 4.0952. Min Range: -4.0952

Max Act: 3.8352. Min Act: -0.1700

Data Index: 2124807 (Open Web Text)

Max Activating Token Index: 909

Text #19

Max Range: 4.0952. Min Range: -4.0952

Max Act: 3.8493. Min Act: -0.1700

Data Index: 4472014 (Open Web Text)

Max Activating Token Index: 951