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

Dataset: Open Web Text

Neuron 2666 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: 3.4975. Min Range: -3.4975

Max Act: 3.4975. Min Act: -0.1700

Data Index: 8117977 (Open Web Text)

Max Activating Token Index: 76

Text #1

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.4351. Min Act: -0.1700

Data Index: 2571321 (Open Web Text)

Max Activating Token Index: 608

Text #2

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.4300. Min Act: -0.1700

Data Index: 1582320 (Open Web Text)

Max Activating Token Index: 475

Text #3

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.4119. Min Act: -0.1700

Data Index: 5461721 (Open Web Text)

Max Activating Token Index: 505

Text #4

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.4409. Min Act: -0.1700

Data Index: 23308 (Open Web Text)

Max Activating Token Index: 655

Text #5

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3979. Min Act: -0.1700

Data Index: 7454075 (Open Web Text)

Max Activating Token Index: 224

Text #6

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.4159. Min Act: -0.1700

Data Index: 593435 (Open Web Text)

Max Activating Token Index: 265

Text #7

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3812. Min Act: -0.1700

Data Index: 8711075 (Open Web Text)

Max Activating Token Index: 223

Text #8

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.4001. Min Act: -0.1700

Data Index: 836514 (Open Web Text)

Max Activating Token Index: 48

Text #9

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.4354. Min Act: -0.1700

Data Index: 6507511 (Open Web Text)

Max Activating Token Index: 247

Text #10

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3719. Min Act: -0.1700

Data Index: 6976806 (Open Web Text)

Max Activating Token Index: 188

Text #11

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3533. Min Act: -0.1700

Data Index: 1666083 (Open Web Text)

Max Activating Token Index: 897

Text #12

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3699. Min Act: -0.1700

Data Index: 1607107 (Open Web Text)

Max Activating Token Index: 658

Text #13

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3818. Min Act: -0.1700

Data Index: 7592814 (Open Web Text)

Max Activating Token Index: 739

Text #14

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3724. Min Act: -0.1700

Data Index: 3679070 (Open Web Text)

Max Activating Token Index: 808

Text #15

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3706. Min Act: -0.1700

Data Index: 4550738 (Open Web Text)

Max Activating Token Index: 283

Text #16

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3156. Min Act: -0.1700

Data Index: 7400317 (Open Web Text)

Max Activating Token Index: 119

Text #17

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3375. Min Act: -0.1700

Data Index: 2129105 (Open Web Text)

Max Activating Token Index: 703

Text #18

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3895. Min Act: -0.1700

Data Index: 8117854 (Open Web Text)

Max Activating Token Index: 630

Text #19

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3472. Min Act: -0.1700

Data Index: 5471711 (Open Web Text)

Max Activating Token Index: 636