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

Dataset: Open Web Text

Neuron 2083 in Layer 2

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: 3.9613. Min Range: -3.9613

Max Act: 3.9467. Min Act: -0.1700

Data Index: 533598 (Open Web Text)

Max Activating Token Index: 230

Text #1

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.9613. Min Act: -0.1700

Data Index: 3908176 (Open Web Text)

Max Activating Token Index: 349

Text #2

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.9144. Min Act: -0.1700

Data Index: 6713286 (Open Web Text)

Max Activating Token Index: 84

Text #3

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.8826. Min Act: -0.1700

Data Index: 8003267 (Open Web Text)

Max Activating Token Index: 975

Text #4

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.8449. Min Act: -0.1700

Data Index: 2038598 (Open Web Text)

Max Activating Token Index: 820

Text #5

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.8520. Min Act: -0.1700

Data Index: 6822581 (Open Web Text)

Max Activating Token Index: 106

Text #6

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.8446. Min Act: -0.1700

Data Index: 1158125 (Open Web Text)

Max Activating Token Index: 108

Text #7

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.8433. Min Act: -0.1700

Data Index: 1345572 (Open Web Text)

Max Activating Token Index: 823

Text #8

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.8249. Min Act: -0.1700

Data Index: 4768603 (Open Web Text)

Max Activating Token Index: 388

Text #9

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.8035. Min Act: -0.1700

Data Index: 4873558 (Open Web Text)

Max Activating Token Index: 276

Text #10

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.7983. Min Act: -0.1700

Data Index: 99074 (Open Web Text)

Max Activating Token Index: 335

Text #11

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.7967. Min Act: -0.1700

Data Index: 1995460 (Open Web Text)

Max Activating Token Index: 747

Text #12

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.7914. Min Act: -0.1700

Data Index: 7971921 (Open Web Text)

Max Activating Token Index: 158

Text #13

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.7892. Min Act: -0.1700

Data Index: 7302174 (Open Web Text)

Max Activating Token Index: 150

Text #14

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.7704. Min Act: -0.1700

Data Index: 4148955 (Open Web Text)

Max Activating Token Index: 279

Text #15

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.8044. Min Act: -0.1700

Data Index: 5918050 (Open Web Text)

Max Activating Token Index: 731

Text #16

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.7733. Min Act: -0.1700

Data Index: 1124091 (Open Web Text)

Max Activating Token Index: 225

Text #17

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.7418. Min Act: -0.1700

Data Index: 990137 (Open Web Text)

Max Activating Token Index: 919

Text #18

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.7739. Min Act: -0.1700

Data Index: 5255349 (Open Web Text)

Max Activating Token Index: 274

Text #19

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.7628. Min Act: -0.1700

Data Index: 1553620 (Open Web Text)

Max Activating Token Index: 114