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

Dataset: Open Web Text

Neuron 2481 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: 5.4043. Min Range: -5.4043

Max Act: 5.4043. Min Act: -0.1700

Data Index: 5091172 (Open Web Text)

Max Activating Token Index: 830

Text #1

Max Range: 5.4043. Min Range: -5.4043

Max Act: 5.3361. Min Act: -0.1700

Data Index: 6328717 (Open Web Text)

Max Activating Token Index: 425

Text #2

Max Range: 5.4043. Min Range: -5.4043

Max Act: 5.3481. Min Act: -0.1700

Data Index: 1406236 (Open Web Text)

Max Activating Token Index: 108

Text #3

Max Range: 5.4043. Min Range: -5.4043

Max Act: 5.3785. Min Act: -0.1700

Data Index: 5165338 (Open Web Text)

Max Activating Token Index: 340

Text #4

Max Range: 5.4043. Min Range: -5.4043

Max Act: 5.2973. Min Act: -0.1700

Data Index: 854910 (Open Web Text)

Max Activating Token Index: 125

Text #5

Max Range: 5.4043. Min Range: -5.4043

Max Act: 5.3305. Min Act: -0.1700

Data Index: 4359692 (Open Web Text)

Max Activating Token Index: 104

Text #6

Max Range: 5.4043. Min Range: -5.4043

Max Act: 5.2685. Min Act: -0.1700

Data Index: 8202406 (Open Web Text)

Max Activating Token Index: 364

Text #7

Max Range: 5.4043. Min Range: -5.4043

Max Act: 5.3182. Min Act: -0.1700

Data Index: 2103913 (Open Web Text)

Max Activating Token Index: 161

Text #8

Max Range: 5.4043. Min Range: -5.4043

Max Act: 5.2518. Min Act: -0.1700

Data Index: 671205 (Open Web Text)

Max Activating Token Index: 553

Text #9

Max Range: 5.4043. Min Range: -5.4043

Max Act: 5.2608. Min Act: -0.1700

Data Index: 1849194 (Open Web Text)

Max Activating Token Index: 281

Text #10

Max Range: 5.4043. Min Range: -5.4043

Max Act: 5.2791. Min Act: -0.1700

Data Index: 2980741 (Open Web Text)

Max Activating Token Index: 32

Text #11

Max Range: 5.4043. Min Range: -5.4043

Max Act: 5.2768. Min Act: -0.1700

Data Index: 6613186 (Open Web Text)

Max Activating Token Index: 897

Text #12

Max Range: 5.4043. Min Range: -5.4043

Max Act: 5.2833. Min Act: -0.1700

Data Index: 2876568 (Open Web Text)

Max Activating Token Index: 280

Text #13

Max Range: 5.4043. Min Range: -5.4043

Max Act: 5.2618. Min Act: -0.1700

Data Index: 6444382 (Open Web Text)

Max Activating Token Index: 1018

Text #14

Max Range: 5.4043. Min Range: -5.4043

Max Act: 5.2587. Min Act: -0.1700

Data Index: 4556234 (Open Web Text)

Max Activating Token Index: 574

Text #15

Max Range: 5.4043. Min Range: -5.4043

Max Act: 5.2548. Min Act: -0.1700

Data Index: 6742042 (Open Web Text)

Max Activating Token Index: 46

Text #16

Max Range: 5.4043. Min Range: -5.4043

Max Act: 5.2371. Min Act: -0.1700

Data Index: 7208694 (Open Web Text)

Max Activating Token Index: 17

Text #17

Max Range: 5.4043. Min Range: -5.4043

Max Act: 5.2400. Min Act: -0.1700

Data Index: 5344004 (Open Web Text)

Max Activating Token Index: 643

Text #18

Max Range: 5.4043. Min Range: -5.4043

Max Act: 5.2424. Min Act: -0.1700

Data Index: 8049005 (Open Web Text)

Max Activating Token Index: 35

Text #19

Max Range: 5.4043. Min Range: -5.4043

Max Act: 5.2535. Min Act: -0.1700

Data Index: 47919 (Open Web Text)

Max Activating Token Index: 18