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

Dataset: Open Web Text

Neuron 950 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: 3.6648. Min Range: -3.6648

Max Act: 3.6504. Min Act: -0.1700

Data Index: 2533476 (Open Web Text)

Max Activating Token Index: 964

Text #1

Max Range: 3.6648. Min Range: -3.6648

Max Act: 3.6648. Min Act: -0.1700

Data Index: 8526332 (Open Web Text)

Max Activating Token Index: 875

Text #2

Max Range: 3.6648. Min Range: -3.6648

Max Act: 3.6414. Min Act: -0.1700

Data Index: 3017211 (Open Web Text)

Max Activating Token Index: 527

Text #3

Max Range: 3.6648. Min Range: -3.6648

Max Act: 3.6048. Min Act: -0.1700

Data Index: 8808749 (Open Web Text)

Max Activating Token Index: 861

Text #4

Max Range: 3.6648. Min Range: -3.6648

Max Act: 3.5861. Min Act: -0.1700

Data Index: 200839 (Open Web Text)

Max Activating Token Index: 915

Text #5

Max Range: 3.6648. Min Range: -3.6648

Max Act: 3.5877. Min Act: -0.1700

Data Index: 1609369 (Open Web Text)

Max Activating Token Index: 917

Text #6

Max Range: 3.6648. Min Range: -3.6648

Max Act: 3.5512. Min Act: -0.1700

Data Index: 2435392 (Open Web Text)

Max Activating Token Index: 818

Text #7

Max Range: 3.6648. Min Range: -3.6648

Max Act: 3.5519. Min Act: -0.1700

Data Index: 8657328 (Open Web Text)

Max Activating Token Index: 26

Text #8

Max Range: 3.6648. Min Range: -3.6648

Max Act: 3.5370. Min Act: -0.1700

Data Index: 56876 (Open Web Text)

Max Activating Token Index: 479

Text #9

Max Range: 3.6648. Min Range: -3.6648

Max Act: 3.5852. Min Act: -0.1700

Data Index: 6619110 (Open Web Text)

Max Activating Token Index: 240

Text #10

Max Range: 3.6648. Min Range: -3.6648

Max Act: 3.5149. Min Act: -0.1700

Data Index: 5258291 (Open Web Text)

Max Activating Token Index: 453

Text #11

Max Range: 3.6648. Min Range: -3.6648

Max Act: 3.5297. Min Act: -0.1700

Data Index: 3129970 (Open Web Text)

Max Activating Token Index: 383

Text #12

Max Range: 3.6648. Min Range: -3.6648

Max Act: 3.5120. Min Act: -0.1700

Data Index: 433956 (Open Web Text)

Max Activating Token Index: 694

Text #13

Max Range: 3.6648. Min Range: -3.6648

Max Act: 3.5155. Min Act: -0.1700

Data Index: 4825570 (Open Web Text)

Max Activating Token Index: 578

Text #14

Max Range: 3.6648. Min Range: -3.6648

Max Act: 3.4918. Min Act: -0.1700

Data Index: 7652301 (Open Web Text)

Max Activating Token Index: 642

Text #15

Max Range: 3.6648. Min Range: -3.6648

Max Act: 3.5150. Min Act: -0.1700

Data Index: 4759339 (Open Web Text)

Max Activating Token Index: 596

Text #16

Max Range: 3.6648. Min Range: -3.6648

Max Act: 3.4893. Min Act: -0.1700

Data Index: 3891046 (Open Web Text)

Max Activating Token Index: 92

Text #17

Max Range: 3.6648. Min Range: -3.6648

Max Act: 3.4981. Min Act: -0.1700

Data Index: 7871391 (Open Web Text)

Max Activating Token Index: 362

Text #18

Max Range: 3.6648. Min Range: -3.6648

Max Act: 3.4856. Min Act: -0.1700

Data Index: 7661975 (Open Web Text)

Max Activating Token Index: 426

Text #19

Max Range: 3.6648. Min Range: -3.6648

Max Act: 3.4848. Min Act: -0.1700

Data Index: 1756455 (Open Web Text)

Max Activating Token Index: 636