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

Dataset: Open Web Text

Neuron 1007 in Layer 6

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: 3.1579. Min Range: -3.1579

Max Act: 3.1579. Min Act: -0.1700

Data Index: 6499544 (Open Web Text)

Max Activating Token Index: 405

Text #1

Max Range: 3.1579. Min Range: -3.1579

Max Act: 3.1263. Min Act: -0.1700

Data Index: 6939693 (Open Web Text)

Max Activating Token Index: 516

Text #2

Max Range: 3.1579. Min Range: -3.1579

Max Act: 3.0747. Min Act: -0.1700

Data Index: 8156695 (Open Web Text)

Max Activating Token Index: 422

Text #3

Max Range: 3.1579. Min Range: -3.1579

Max Act: 3.0632. Min Act: -0.1700

Data Index: 6118380 (Open Web Text)

Max Activating Token Index: 762

Text #4

Max Range: 3.1579. Min Range: -3.1579

Max Act: 3.0667. Min Act: -0.1700

Data Index: 6778362 (Open Web Text)

Max Activating Token Index: 295

Text #5

Max Range: 3.1579. Min Range: -3.1579

Max Act: 3.0742. Min Act: -0.1700

Data Index: 4429152 (Open Web Text)

Max Activating Token Index: 987

Text #6

Max Range: 3.1579. Min Range: -3.1579

Max Act: 3.0422. Min Act: -0.1700

Data Index: 8561307 (Open Web Text)

Max Activating Token Index: 926

Text #7

Max Range: 3.1579. Min Range: -3.1579

Max Act: 3.0163. Min Act: -0.1700

Data Index: 7493320 (Open Web Text)

Max Activating Token Index: 853

Text #8

Max Range: 3.1579. Min Range: -3.1579

Max Act: 3.0139. Min Act: -0.1700

Data Index: 6243551 (Open Web Text)

Max Activating Token Index: 160

Text #9

Max Range: 3.1579. Min Range: -3.1579

Max Act: 3.0115. Min Act: -0.1700

Data Index: 176942 (Open Web Text)

Max Activating Token Index: 941

Text #10

Max Range: 3.1579. Min Range: -3.1579

Max Act: 3.0150. Min Act: -0.1700

Data Index: 8326175 (Open Web Text)

Max Activating Token Index: 788

Text #11

Max Range: 3.1579. Min Range: -3.1579

Max Act: 2.9979. Min Act: -0.1700

Data Index: 4935296 (Open Web Text)

Max Activating Token Index: 477

Text #12

Max Range: 3.1579. Min Range: -3.1579

Max Act: 2.9887. Min Act: -0.1700

Data Index: 6777295 (Open Web Text)

Max Activating Token Index: 322

Text #13

Max Range: 3.1579. Min Range: -3.1579

Max Act: 2.9700. Min Act: -0.1700

Data Index: 7305410 (Open Web Text)

Max Activating Token Index: 894

Text #14

Max Range: 3.1579. Min Range: -3.1579

Max Act: 2.9363. Min Act: -0.1700

Data Index: 4979677 (Open Web Text)

Max Activating Token Index: 769

Text #15

Max Range: 3.1579. Min Range: -3.1579

Max Act: 2.9410. Min Act: -0.1700

Data Index: 8601044 (Open Web Text)

Max Activating Token Index: 866

Text #16

Max Range: 3.1579. Min Range: -3.1579

Max Act: 2.9699. Min Act: -0.1700

Data Index: 8270845 (Open Web Text)

Max Activating Token Index: 413

Text #17

Max Range: 3.1579. Min Range: -3.1579

Max Act: 2.9433. Min Act: -0.1700

Data Index: 4735656 (Open Web Text)

Max Activating Token Index: 634

Text #18

Max Range: 3.1579. Min Range: -3.1579

Max Act: 2.9416. Min Act: -0.1700

Data Index: 6521967 (Open Web Text)

Max Activating Token Index: 566

Text #19

Max Range: 3.1579. Min Range: -3.1579

Max Act: 2.9505. Min Act: -0.1700

Data Index: 7212012 (Open Web Text)

Max Activating Token Index: 95