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

Dataset: Open Web Text

Neuron 224 in Layer 3

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: 5.0823. Min Range: -5.0823

Max Act: 5.0823. Min Act: -0.1700

Data Index: 8688059 (Open Web Text)

Max Activating Token Index: 1012

Text #1

Max Range: 5.0823. Min Range: -5.0823

Max Act: 5.0150. Min Act: -0.1700

Data Index: 1297892 (Open Web Text)

Max Activating Token Index: 873

Text #2

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.9381. Min Act: -0.1700

Data Index: 3090664 (Open Web Text)

Max Activating Token Index: 567

Text #3

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.9076. Min Act: -0.1700

Data Index: 2210448 (Open Web Text)

Max Activating Token Index: 755

Text #4

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.9307. Min Act: -0.1700

Data Index: 6881078 (Open Web Text)

Max Activating Token Index: 853

Text #5

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.9513. Min Act: -0.1700

Data Index: 5664683 (Open Web Text)

Max Activating Token Index: 1017

Text #6

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.9391. Min Act: -0.1700

Data Index: 1664379 (Open Web Text)

Max Activating Token Index: 917

Text #7

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.9522. Min Act: -0.1700

Data Index: 14351 (Open Web Text)

Max Activating Token Index: 411

Text #8

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.9566. Min Act: -0.1700

Data Index: 7807195 (Open Web Text)

Max Activating Token Index: 492

Text #9

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.8896. Min Act: -0.1700

Data Index: 6599730 (Open Web Text)

Max Activating Token Index: 1000

Text #10

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.9289. Min Act: -0.1700

Data Index: 3244325 (Open Web Text)

Max Activating Token Index: 667

Text #11

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.8993. Min Act: -0.1700

Data Index: 3642835 (Open Web Text)

Max Activating Token Index: 609

Text #12

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.8731. Min Act: -0.1700

Data Index: 5371019 (Open Web Text)

Max Activating Token Index: 566

Text #13

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.8941. Min Act: -0.1700

Data Index: 2501187 (Open Web Text)

Max Activating Token Index: 587

Text #14

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.8997. Min Act: -0.1700

Data Index: 683804 (Open Web Text)

Max Activating Token Index: 441

Text #15

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.8629. Min Act: -0.1700

Data Index: 6758607 (Open Web Text)

Max Activating Token Index: 694

Text #16

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.8286. Min Act: -0.1700

Data Index: 2399058 (Open Web Text)

Max Activating Token Index: 774

Text #17

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.8678. Min Act: -0.1700

Data Index: 8335591 (Open Web Text)

Max Activating Token Index: 506

Text #18

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.8546. Min Act: -0.1700

Data Index: 5039492 (Open Web Text)

Max Activating Token Index: 658

Text #19

Max Range: 5.0823. Min Range: -5.0823

Max Act: 4.8120. Min Act: -0.1700

Data Index: 6808853 (Open Web Text)

Max Activating Token Index: 921