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

Dataset: Open Web Text

Neuron 1894 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: 3.6461. Min Range: -3.6461

Max Act: 3.6461. Min Act: -0.1700

Data Index: 1693924 (Open Web Text)

Max Activating Token Index: 383

Text #1

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.5746. Min Act: -0.1700

Data Index: 4157576 (Open Web Text)

Max Activating Token Index: 427

Text #2

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.5824. Min Act: -0.1700

Data Index: 4700670 (Open Web Text)

Max Activating Token Index: 1004

Text #3

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.5586. Min Act: -0.1700

Data Index: 4127244 (Open Web Text)

Max Activating Token Index: 436

Text #4

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.5663. Min Act: -0.1700

Data Index: 7967537 (Open Web Text)

Max Activating Token Index: 751

Text #5

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.5004. Min Act: -0.1700

Data Index: 7345447 (Open Web Text)

Max Activating Token Index: 616

Text #6

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.4878. Min Act: -0.1700

Data Index: 6369227 (Open Web Text)

Max Activating Token Index: 823

Text #7

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.4722. Min Act: -0.1700

Data Index: 3464514 (Open Web Text)

Max Activating Token Index: 723

Text #8

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.3943. Min Act: -0.1700

Data Index: 2076775 (Open Web Text)

Max Activating Token Index: 600

Text #9

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.4761. Min Act: -0.1700

Data Index: 876180 (Open Web Text)

Max Activating Token Index: 173

Text #10

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.4062. Min Act: -0.1700

Data Index: 4451460 (Open Web Text)

Max Activating Token Index: 137

Text #11

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.4182. Min Act: -0.1700

Data Index: 908483 (Open Web Text)

Max Activating Token Index: 284

Text #12

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.4227. Min Act: -0.1700

Data Index: 4083813 (Open Web Text)

Max Activating Token Index: 833

Text #13

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.3990. Min Act: -0.1700

Data Index: 5113419 (Open Web Text)

Max Activating Token Index: 777

Text #14

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.3852. Min Act: -0.1700

Data Index: 4210682 (Open Web Text)

Max Activating Token Index: 120

Text #15

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.3767. Min Act: -0.1700

Data Index: 876178 (Open Web Text)

Max Activating Token Index: 590

Text #16

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.3644. Min Act: -0.1700

Data Index: 7457106 (Open Web Text)

Max Activating Token Index: 247

Text #17

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.3584. Min Act: -0.1700

Data Index: 3864994 (Open Web Text)

Max Activating Token Index: 733

Text #18

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.3408. Min Act: -0.1700

Data Index: 846494 (Open Web Text)

Max Activating Token Index: 646

Text #19

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.3245. Min Act: -0.1700

Data Index: 924893 (Open Web Text)

Max Activating Token Index: 766