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

Dataset: Open Web Text

Neuron 1534 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: 6.0426. Min Range: -6.0426

Max Act: 6.0426. Min Act: -0.1700

Data Index: 6268852 (Open Web Text)

Max Activating Token Index: 714

Text #1

Max Range: 6.0426. Min Range: -6.0426

Max Act: 5.9596. Min Act: -0.1700

Data Index: 4458077 (Open Web Text)

Max Activating Token Index: 384

Text #2

Max Range: 6.0426. Min Range: -6.0426

Max Act: 6.0169. Min Act: -0.1700

Data Index: 7954621 (Open Web Text)

Max Activating Token Index: 143

Text #3

Max Range: 6.0426. Min Range: -6.0426

Max Act: 5.8846. Min Act: -0.1700

Data Index: 7686449 (Open Web Text)

Max Activating Token Index: 456

Text #4

Max Range: 6.0426. Min Range: -6.0426

Max Act: 5.9401. Min Act: -0.1700

Data Index: 1980535 (Open Web Text)

Max Activating Token Index: 965

Text #5

Max Range: 6.0426. Min Range: -6.0426

Max Act: 5.8788. Min Act: -0.1700

Data Index: 315721 (Open Web Text)

Max Activating Token Index: 898

Text #6

Max Range: 6.0426. Min Range: -6.0426

Max Act: 5.8587. Min Act: -0.1700

Data Index: 5382720 (Open Web Text)

Max Activating Token Index: 779

Text #7

Max Range: 6.0426. Min Range: -6.0426

Max Act: 5.9528. Min Act: -0.1700

Data Index: 4147084 (Open Web Text)

Max Activating Token Index: 906

Text #8

Max Range: 6.0426. Min Range: -6.0426

Max Act: 5.8552. Min Act: -0.1700

Data Index: 8450203 (Open Web Text)

Max Activating Token Index: 525

Text #9

Max Range: 6.0426. Min Range: -6.0426

Max Act: 5.8946. Min Act: -0.1700

Data Index: 6457491 (Open Web Text)

Max Activating Token Index: 413

Text #10

Max Range: 6.0426. Min Range: -6.0426

Max Act: 5.8810. Min Act: -0.1700

Data Index: 7604088 (Open Web Text)

Max Activating Token Index: 1016

Text #11

Max Range: 6.0426. Min Range: -6.0426

Max Act: 5.8798. Min Act: -0.1700

Data Index: 5997485 (Open Web Text)

Max Activating Token Index: 330

Text #12

Max Range: 6.0426. Min Range: -6.0426

Max Act: 5.8832. Min Act: -0.1700

Data Index: 315858 (Open Web Text)

Max Activating Token Index: 264

Text #13

Max Range: 6.0426. Min Range: -6.0426

Max Act: 5.8374. Min Act: -0.1700

Data Index: 569526 (Open Web Text)

Max Activating Token Index: 300

Text #14

Max Range: 6.0426. Min Range: -6.0426

Max Act: 5.8097. Min Act: -0.1700

Data Index: 6223455 (Open Web Text)

Max Activating Token Index: 838

Text #15

Max Range: 6.0426. Min Range: -6.0426

Max Act: 5.8899. Min Act: -0.1700

Data Index: 3489943 (Open Web Text)

Max Activating Token Index: 389

Text #16

Max Range: 6.0426. Min Range: -6.0426

Max Act: 5.7465. Min Act: -0.1700

Data Index: 6210186 (Open Web Text)

Max Activating Token Index: 1016

Text #17

Max Range: 6.0426. Min Range: -6.0426

Max Act: 5.8201. Min Act: -0.1700

Data Index: 2648678 (Open Web Text)

Max Activating Token Index: 780

Text #18

Max Range: 6.0426. Min Range: -6.0426

Max Act: 5.7540. Min Act: -0.1700

Data Index: 2223505 (Open Web Text)

Max Activating Token Index: 499

Text #19

Max Range: 6.0426. Min Range: -6.0426

Max Act: 5.7780. Min Act: -0.1700

Data Index: 6660695 (Open Web Text)

Max Activating Token Index: 396