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

Dataset: Open Web Text

Neuron 348 in Layer 0

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: 1.5141. Min Range: -1.5141

Max Act: 1.5141. Min Act: -0.1613

Data Index: 3314704 (Open Web Text)

Max Activating Token Index: 536

Text #1

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.4987. Min Act: -0.1673

Data Index: 7128159 (Open Web Text)

Max Activating Token Index: 116

Text #2

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.5006. Min Act: -0.1684

Data Index: 2777922 (Open Web Text)

Max Activating Token Index: 658

Text #3

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.4944. Min Act: -0.0685

Data Index: 4749091 (Open Web Text)

Max Activating Token Index: 171

Text #4

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.4916. Min Act: -0.1697

Data Index: 7821901 (Open Web Text)

Max Activating Token Index: 283

Text #5

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.4891. Min Act: -0.1700

Data Index: 5384864 (Open Web Text)

Max Activating Token Index: 356

Text #6

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.4960. Min Act: -0.1653

Data Index: 4987570 (Open Web Text)

Max Activating Token Index: 510

Text #7

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.4866. Min Act: -0.0238

Data Index: 4749092 (Open Web Text)

Max Activating Token Index: 199

Text #8

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.4929. Min Act: -0.1700

Data Index: 7984615 (Open Web Text)

Max Activating Token Index: 646

Text #9

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.4907. Min Act: -0.1698

Data Index: 2484546 (Open Web Text)

Max Activating Token Index: 484

Text #10

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.4838. Min Act: -0.1699

Data Index: 3400248 (Open Web Text)

Max Activating Token Index: 382

Text #11

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.4891. Min Act: -0.1690

Data Index: 8018852 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.4868. Min Act: -0.1698

Data Index: 978067 (Open Web Text)

Max Activating Token Index: 770

Text #13

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.4804. Min Act: -0.1669

Data Index: 1523513 (Open Web Text)

Max Activating Token Index: 1006

Text #14

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.4842. Min Act: -0.1685

Data Index: 706897 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.4790. Min Act: -0.1700

Data Index: 4435489 (Open Web Text)

Max Activating Token Index: 447

Text #16

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.4807. Min Act: -0.1698

Data Index: 1809467 (Open Web Text)

Max Activating Token Index: 196

Text #17

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.4771. Min Act: -0.1660

Data Index: 5784303 (Open Web Text)

Max Activating Token Index: 763

Text #18

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.4755. Min Act: -0.1700

Data Index: 6679916 (Open Web Text)

Max Activating Token Index: 605

Text #19

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.4768. Min Act: -0.1688

Data Index: 1649629 (Open Web Text)

Max Activating Token Index: 723