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

Dataset: Open Web Text

Neuron 2419 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: 4.2417. Min Range: -4.2417

Max Act: 4.2417. Min Act: -0.1700

Data Index: 7047695 (Open Web Text)

Max Activating Token Index: 437

Text #1

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.2377. Min Act: -0.1700

Data Index: 7715412 (Open Web Text)

Max Activating Token Index: 686

Text #2

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.2016. Min Act: -0.1700

Data Index: 2885686 (Open Web Text)

Max Activating Token Index: 752

Text #3

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.2069. Min Act: -0.1700

Data Index: 4630683 (Open Web Text)

Max Activating Token Index: 568

Text #4

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.1875. Min Act: -0.1700

Data Index: 5013439 (Open Web Text)

Max Activating Token Index: 161

Text #5

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.1714. Min Act: -0.1700

Data Index: 6402674 (Open Web Text)

Max Activating Token Index: 691

Text #6

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.1579. Min Act: -0.1700

Data Index: 1690709 (Open Web Text)

Max Activating Token Index: 823

Text #7

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.1472. Min Act: -0.1700

Data Index: 8068620 (Open Web Text)

Max Activating Token Index: 668

Text #8

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.1087. Min Act: -0.1700

Data Index: 5781629 (Open Web Text)

Max Activating Token Index: 732

Text #9

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.1132. Min Act: -0.1700

Data Index: 4223584 (Open Web Text)

Max Activating Token Index: 721

Text #10

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.0784. Min Act: -0.1700

Data Index: 8066852 (Open Web Text)

Max Activating Token Index: 451

Text #11

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.0903. Min Act: -0.1700

Data Index: 7640935 (Open Web Text)

Max Activating Token Index: 865

Text #12

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.0849. Min Act: -0.1700

Data Index: 1512853 (Open Web Text)

Max Activating Token Index: 658

Text #13

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.0816. Min Act: -0.1700

Data Index: 7938222 (Open Web Text)

Max Activating Token Index: 475

Text #14

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.0545. Min Act: -0.1700

Data Index: 1362512 (Open Web Text)

Max Activating Token Index: 920

Text #15

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.0469. Min Act: -0.1700

Data Index: 1403413 (Open Web Text)

Max Activating Token Index: 544

Text #16

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.0480. Min Act: -0.1700

Data Index: 3248109 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.0705. Min Act: -0.1700

Data Index: 4568289 (Open Web Text)

Max Activating Token Index: 594

Text #18

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.0806. Min Act: -0.1700

Data Index: 3478946 (Open Web Text)

Max Activating Token Index: 542

Text #19

Max Range: 4.2417. Min Range: -4.2417

Max Act: 4.0566. Min Act: -0.1700

Data Index: 5061358 (Open Web Text)

Max Activating Token Index: 375