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

Dataset: Open Web Text

Neuron 100 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: 4.1607. Min Range: -4.1607

Max Act: 4.1607. Min Act: -0.1700

Data Index: 1424681 (Open Web Text)

Max Activating Token Index: 879

Text #1

Max Range: 4.1607. Min Range: -4.1607

Max Act: 4.0935. Min Act: -0.1700

Data Index: 8010316 (Open Web Text)

Max Activating Token Index: 636

Text #2

Max Range: 4.1607. Min Range: -4.1607

Max Act: 4.0545. Min Act: -0.1700

Data Index: 6869594 (Open Web Text)

Max Activating Token Index: 402

Text #3

Max Range: 4.1607. Min Range: -4.1607

Max Act: 4.0288. Min Act: -0.1700

Data Index: 7778043 (Open Web Text)

Max Activating Token Index: 315

Text #4

Max Range: 4.1607. Min Range: -4.1607

Max Act: 4.0355. Min Act: -0.1700

Data Index: 3550426 (Open Web Text)

Max Activating Token Index: 740

Text #5

Max Range: 4.1607. Min Range: -4.1607

Max Act: 4.0094. Min Act: -0.1700

Data Index: 5968175 (Open Web Text)

Max Activating Token Index: 188

Text #6

Max Range: 4.1607. Min Range: -4.1607

Max Act: 3.9840. Min Act: -0.1700

Data Index: 1947075 (Open Web Text)

Max Activating Token Index: 286

Text #7

Max Range: 4.1607. Min Range: -4.1607

Max Act: 4.0206. Min Act: -0.1700

Data Index: 722483 (Open Web Text)

Max Activating Token Index: 179

Text #8

Max Range: 4.1607. Min Range: -4.1607

Max Act: 3.9801. Min Act: -0.1700

Data Index: 1594301 (Open Web Text)

Max Activating Token Index: 212

Text #9

Max Range: 4.1607. Min Range: -4.1607

Max Act: 3.9952. Min Act: -0.1700

Data Index: 7912830 (Open Web Text)

Max Activating Token Index: 825

Text #10

Max Range: 4.1607. Min Range: -4.1607

Max Act: 3.9910. Min Act: -0.1700

Data Index: 7345414 (Open Web Text)

Max Activating Token Index: 234

Text #11

Max Range: 4.1607. Min Range: -4.1607

Max Act: 3.9999. Min Act: -0.1700

Data Index: 4993546 (Open Web Text)

Max Activating Token Index: 131

Text #12

Max Range: 4.1607. Min Range: -4.1607

Max Act: 3.9709. Min Act: -0.1700

Data Index: 6719219 (Open Web Text)

Max Activating Token Index: 566

Text #13

Max Range: 4.1607. Min Range: -4.1607

Max Act: 3.9750. Min Act: -0.1700

Data Index: 2509310 (Open Web Text)

Max Activating Token Index: 119

Text #14

Max Range: 4.1607. Min Range: -4.1607

Max Act: 3.9801. Min Act: -0.1700

Data Index: 3910555 (Open Web Text)

Max Activating Token Index: 545

Text #15

Max Range: 4.1607. Min Range: -4.1607

Max Act: 3.9625. Min Act: -0.1700

Data Index: 1966306 (Open Web Text)

Max Activating Token Index: 130

Text #16

Max Range: 4.1607. Min Range: -4.1607

Max Act: 3.9734. Min Act: -0.1700

Data Index: 7078820 (Open Web Text)

Max Activating Token Index: 640

Text #17

Max Range: 4.1607. Min Range: -4.1607

Max Act: 3.9770. Min Act: -0.1700

Data Index: 4308834 (Open Web Text)

Max Activating Token Index: 288

Text #18

Max Range: 4.1607. Min Range: -4.1607

Max Act: 3.9652. Min Act: -0.1700

Data Index: 4363157 (Open Web Text)

Max Activating Token Index: 111

Text #19

Max Range: 4.1607. Min Range: -4.1607

Max Act: 3.9739. Min Act: -0.1700

Data Index: 5784914 (Open Web Text)

Max Activating Token Index: 171