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

Dataset: Open Web Text

Neuron 2522 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: 2.1937. Min Range: -2.1937

Max Act: 2.1937. Min Act: -0.1700

Data Index: 571674 (Open Web Text)

Max Activating Token Index: 607

Text #1

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.1413. Min Act: -0.1700

Data Index: 8376964 (Open Web Text)

Max Activating Token Index: 355

Text #2

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.1506. Min Act: -0.1700

Data Index: 3914496 (Open Web Text)

Max Activating Token Index: 312

Text #3

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.1262. Min Act: -0.1700

Data Index: 6211799 (Open Web Text)

Max Activating Token Index: 456

Text #4

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.1062. Min Act: -0.1700

Data Index: 1684826 (Open Web Text)

Max Activating Token Index: 765

Text #5

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.0971. Min Act: -0.1700

Data Index: 4140914 (Open Web Text)

Max Activating Token Index: 506

Text #6

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.0596. Min Act: -0.1700

Data Index: 4055198 (Open Web Text)

Max Activating Token Index: 528

Text #7

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.0827. Min Act: -0.1700

Data Index: 2076655 (Open Web Text)

Max Activating Token Index: 222

Text #8

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.0599. Min Act: -0.1700

Data Index: 3975015 (Open Web Text)

Max Activating Token Index: 634

Text #9

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.0830. Min Act: -0.1700

Data Index: 5283158 (Open Web Text)

Max Activating Token Index: 360

Text #10

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.0538. Min Act: -0.1700

Data Index: 4916706 (Open Web Text)

Max Activating Token Index: 124

Text #11

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.0460. Min Act: -0.1700

Data Index: 5674976 (Open Web Text)

Max Activating Token Index: 815

Text #12

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.0557. Min Act: -0.1700

Data Index: 7933740 (Open Web Text)

Max Activating Token Index: 658

Text #13

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.0445. Min Act: -0.1700

Data Index: 2967841 (Open Web Text)

Max Activating Token Index: 316

Text #14

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.0530. Min Act: -0.1700

Data Index: 4198812 (Open Web Text)

Max Activating Token Index: 95

Text #15

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.0618. Min Act: -0.1700

Data Index: 8023750 (Open Web Text)

Max Activating Token Index: 842

Text #16

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.0563. Min Act: -0.1700

Data Index: 8180067 (Open Web Text)

Max Activating Token Index: 711

Text #17

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.0480. Min Act: -0.1700

Data Index: 3422049 (Open Web Text)

Max Activating Token Index: 550

Text #18

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.0493. Min Act: -0.1700

Data Index: 2157937 (Open Web Text)

Max Activating Token Index: 161

Text #19

Max Range: 2.1937. Min Range: -2.1937

Max Act: 2.0576. Min Act: -0.1700

Data Index: 6194171 (Open Web Text)

Max Activating Token Index: 720