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

Dataset: Open Web Text

Neuron 854 in Layer 4

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: 4.5064. Min Range: -4.5064

Max Act: 4.4952. Min Act: -0.1700

Data Index: 4060520 (Open Web Text)

Max Activating Token Index: 636

Text #1

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.4962. Min Act: -0.1700

Data Index: 4835326 (Open Web Text)

Max Activating Token Index: 602

Text #2

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.5064. Min Act: -0.1700

Data Index: 410009 (Open Web Text)

Max Activating Token Index: 1009

Text #3

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.4744. Min Act: -0.1700

Data Index: 1742298 (Open Web Text)

Max Activating Token Index: 441

Text #4

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.4162. Min Act: -0.1700

Data Index: 3046610 (Open Web Text)

Max Activating Token Index: 570

Text #5

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.4052. Min Act: -0.1700

Data Index: 151762 (Open Web Text)

Max Activating Token Index: 307

Text #6

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.3744. Min Act: -0.1700

Data Index: 2711184 (Open Web Text)

Max Activating Token Index: 461

Text #7

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.3677. Min Act: -0.1700

Data Index: 4038363 (Open Web Text)

Max Activating Token Index: 867

Text #8

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.3776. Min Act: -0.1700

Data Index: 5563411 (Open Web Text)

Max Activating Token Index: 71

Text #9

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.3820. Min Act: -0.1700

Data Index: 1621739 (Open Web Text)

Max Activating Token Index: 417

Text #10

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.3473. Min Act: -0.1700

Data Index: 5056519 (Open Web Text)

Max Activating Token Index: 504

Text #11

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.3427. Min Act: -0.1700

Data Index: 5847682 (Open Web Text)

Max Activating Token Index: 243

Text #12

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.2846. Min Act: -0.1700

Data Index: 928045 (Open Web Text)

Max Activating Token Index: 790

Text #13

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.3318. Min Act: -0.1700

Data Index: 5217741 (Open Web Text)

Max Activating Token Index: 285

Text #14

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.3171. Min Act: -0.1700

Data Index: 7932690 (Open Web Text)

Max Activating Token Index: 416

Text #15

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.3231. Min Act: -0.1700

Data Index: 860347 (Open Web Text)

Max Activating Token Index: 175

Text #16

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.2999. Min Act: -0.1700

Data Index: 1008731 (Open Web Text)

Max Activating Token Index: 691

Text #17

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.3232. Min Act: -0.1700

Data Index: 1646727 (Open Web Text)

Max Activating Token Index: 520

Text #18

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.2934. Min Act: -0.1700

Data Index: 2611194 (Open Web Text)

Max Activating Token Index: 734

Text #19

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.2762. Min Act: -0.1700

Data Index: 1042703 (Open Web Text)

Max Activating Token Index: 648