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

Dataset: Open Web Text

Neuron 1234 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: 3.8857. Min Range: -3.8857

Max Act: 3.8732. Min Act: -0.1700

Data Index: 6810174 (Open Web Text)

Max Activating Token Index: 201

Text #1

Max Range: 3.8857. Min Range: -3.8857

Max Act: 3.8817. Min Act: -0.1700

Data Index: 7922930 (Open Web Text)

Max Activating Token Index: 963

Text #2

Max Range: 3.8857. Min Range: -3.8857

Max Act: 3.8857. Min Act: -0.1700

Data Index: 4354819 (Open Web Text)

Max Activating Token Index: 242

Text #3

Max Range: 3.8857. Min Range: -3.8857

Max Act: 3.8482. Min Act: -0.1700

Data Index: 8703599 (Open Web Text)

Max Activating Token Index: 741

Text #4

Max Range: 3.8857. Min Range: -3.8857

Max Act: 3.8508. Min Act: -0.1700

Data Index: 2849654 (Open Web Text)

Max Activating Token Index: 599

Text #5

Max Range: 3.8857. Min Range: -3.8857

Max Act: 3.8477. Min Act: -0.1700

Data Index: 3424031 (Open Web Text)

Max Activating Token Index: 777

Text #6

Max Range: 3.8857. Min Range: -3.8857

Max Act: 3.8435. Min Act: -0.1700

Data Index: 7816516 (Open Web Text)

Max Activating Token Index: 145

Text #7

Max Range: 3.8857. Min Range: -3.8857

Max Act: 3.8259. Min Act: -0.1700

Data Index: 423005 (Open Web Text)

Max Activating Token Index: 673

Text #8

Max Range: 3.8857. Min Range: -3.8857

Max Act: 3.8554. Min Act: -0.1700

Data Index: 1713260 (Open Web Text)

Max Activating Token Index: 874

Text #9

Max Range: 3.8857. Min Range: -3.8857

Max Act: 3.8047. Min Act: -0.1700

Data Index: 8361140 (Open Web Text)

Max Activating Token Index: 657

Text #10

Max Range: 3.8857. Min Range: -3.8857

Max Act: 3.7852. Min Act: -0.1700

Data Index: 4412259 (Open Web Text)

Max Activating Token Index: 165

Text #11

Max Range: 3.8857. Min Range: -3.8857

Max Act: 3.7929. Min Act: -0.1700

Data Index: 8435784 (Open Web Text)

Max Activating Token Index: 210

Text #12

Max Range: 3.8857. Min Range: -3.8857

Max Act: 3.7893. Min Act: -0.1700

Data Index: 4941382 (Open Web Text)

Max Activating Token Index: 724

Text #13

Max Range: 3.8857. Min Range: -3.8857

Max Act: 3.7971. Min Act: -0.1700

Data Index: 4248093 (Open Web Text)

Max Activating Token Index: 791

Text #14

Max Range: 3.8857. Min Range: -3.8857

Max Act: 3.7879. Min Act: -0.1700

Data Index: 1110666 (Open Web Text)

Max Activating Token Index: 1003

Text #15

Max Range: 3.8857. Min Range: -3.8857

Max Act: 3.7987. Min Act: -0.1700

Data Index: 1712450 (Open Web Text)

Max Activating Token Index: 825

Text #16

Max Range: 3.8857. Min Range: -3.8857

Max Act: 3.7536. Min Act: -0.1700

Data Index: 4438404 (Open Web Text)

Max Activating Token Index: 695

Text #17

Max Range: 3.8857. Min Range: -3.8857

Max Act: 3.7774. Min Act: -0.1700

Data Index: 4134232 (Open Web Text)

Max Activating Token Index: 635

Text #18

Max Range: 3.8857. Min Range: -3.8857

Max Act: 3.7565. Min Act: -0.1700

Data Index: 7544850 (Open Web Text)

Max Activating Token Index: 813

Text #19

Max Range: 3.8857. Min Range: -3.8857

Max Act: 3.7675. Min Act: -0.1700

Data Index: 5197970 (Open Web Text)

Max Activating Token Index: 705