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

Dataset: Open Web Text

Neuron 1146 in Layer 4

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: 3.8690. Min Range: -3.8690

Max Act: 3.8690. Min Act: -0.1700

Data Index: 334471 (Open Web Text)

Max Activating Token Index: 267

Text #1

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.8636. Min Act: -0.1700

Data Index: 3940729 (Open Web Text)

Max Activating Token Index: 877

Text #2

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.8262. Min Act: -0.1700

Data Index: 5679493 (Open Web Text)

Max Activating Token Index: 337

Text #3

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.8495. Min Act: -0.1700

Data Index: 896801 (Open Web Text)

Max Activating Token Index: 309

Text #4

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.7884. Min Act: -0.1700

Data Index: 6793458 (Open Web Text)

Max Activating Token Index: 708

Text #5

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.7498. Min Act: -0.1700

Data Index: 3764284 (Open Web Text)

Max Activating Token Index: 693

Text #6

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.7829. Min Act: -0.1700

Data Index: 7349099 (Open Web Text)

Max Activating Token Index: 975

Text #7

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.7462. Min Act: -0.1700

Data Index: 2856608 (Open Web Text)

Max Activating Token Index: 736

Text #8

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.7261. Min Act: -0.1700

Data Index: 7090510 (Open Web Text)

Max Activating Token Index: 896

Text #9

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.7367. Min Act: -0.1700

Data Index: 6558639 (Open Web Text)

Max Activating Token Index: 174

Text #10

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.7441. Min Act: -0.1700

Data Index: 7763547 (Open Web Text)

Max Activating Token Index: 939

Text #11

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.6850. Min Act: -0.1700

Data Index: 1472661 (Open Web Text)

Max Activating Token Index: 327

Text #12

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.6784. Min Act: -0.1700

Data Index: 5142663 (Open Web Text)

Max Activating Token Index: 227

Text #13

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.6709. Min Act: -0.1700

Data Index: 3124843 (Open Web Text)

Max Activating Token Index: 964

Text #14

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.6737. Min Act: -0.1700

Data Index: 4870126 (Open Web Text)

Max Activating Token Index: 389

Text #15

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.6813. Min Act: -0.1700

Data Index: 1157346 (Open Web Text)

Max Activating Token Index: 782

Text #16

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.6795. Min Act: -0.1700

Data Index: 6194252 (Open Web Text)

Max Activating Token Index: 989

Text #17

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.6604. Min Act: -0.1700

Data Index: 6443992 (Open Web Text)

Max Activating Token Index: 863

Text #18

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.6652. Min Act: -0.1700

Data Index: 2820304 (Open Web Text)

Max Activating Token Index: 415

Text #19

Max Range: 3.8690. Min Range: -3.8690

Max Act: 3.6552. Min Act: -0.1700

Data Index: 3439742 (Open Web Text)

Max Activating Token Index: 457