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

Dataset: Open Web Text

Neuron 655 in Layer 5

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: 4.0432. Min Range: -4.0432

Max Act: 4.0432. Min Act: -0.1700

Data Index: 6740713 (Open Web Text)

Max Activating Token Index: 39

Text #1

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.9422. Min Act: -0.1700

Data Index: 6660694 (Open Web Text)

Max Activating Token Index: 183

Text #2

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.8122. Min Act: -0.1699

Data Index: 5147125 (Open Web Text)

Max Activating Token Index: 701

Text #3

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.8051. Min Act: -0.1700

Data Index: 7789051 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.7898. Min Act: -0.1700

Data Index: 673652 (Open Web Text)

Max Activating Token Index: 557

Text #5

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.7837. Min Act: -0.1700

Data Index: 7205557 (Open Web Text)

Max Activating Token Index: 635

Text #6

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.7745. Min Act: -0.1700

Data Index: 6740715 (Open Web Text)

Max Activating Token Index: 448

Text #7

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.7430. Min Act: -0.1700

Data Index: 6986626 (Open Web Text)

Max Activating Token Index: 717

Text #8

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.7418. Min Act: -0.1700

Data Index: 1489967 (Open Web Text)

Max Activating Token Index: 188

Text #9

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.7584. Min Act: -0.1700

Data Index: 1531787 (Open Web Text)

Max Activating Token Index: 933

Text #10

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.7703. Min Act: -0.1700

Data Index: 7205558 (Open Web Text)

Max Activating Token Index: 749

Text #11

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.7061. Min Act: -0.1700

Data Index: 7539474 (Open Web Text)

Max Activating Token Index: 558

Text #12

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.6948. Min Act: -0.1700

Data Index: 591208 (Open Web Text)

Max Activating Token Index: 699

Text #13

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.7139. Min Act: -0.1700

Data Index: 8282998 (Open Web Text)

Max Activating Token Index: 915

Text #14

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.6682. Min Act: -0.1700

Data Index: 8234139 (Open Web Text)

Max Activating Token Index: 526

Text #15

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.6786. Min Act: -0.1692

Data Index: 45339 (Open Web Text)

Max Activating Token Index: 971

Text #16

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.6766. Min Act: -0.1700

Data Index: 3937119 (Open Web Text)

Max Activating Token Index: 939

Text #17

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.6784. Min Act: -0.1700

Data Index: 7712424 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.6570. Min Act: -0.1700

Data Index: 159617 (Open Web Text)

Max Activating Token Index: 593

Text #19

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.6438. Min Act: -0.1700

Data Index: 1275972 (Open Web Text)

Max Activating Token Index: 1005