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

Dataset: Open Web Text

Neuron 37 in Layer 1

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: 2.3619. Min Range: -2.3619

Max Act: 2.3619. Min Act: -0.1700

Data Index: 5606475 (Open Web Text)

Max Activating Token Index: 438

Text #1

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.3320. Min Act: -0.1700

Data Index: 6936928 (Open Web Text)

Max Activating Token Index: 940

Text #2

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.2793. Min Act: -0.1700

Data Index: 428846 (Open Web Text)

Max Activating Token Index: 496

Text #3

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.2146. Min Act: -0.1700

Data Index: 7822750 (Open Web Text)

Max Activating Token Index: 835

Text #4

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.1516. Min Act: -0.1700

Data Index: 2933380 (Open Web Text)

Max Activating Token Index: 788

Text #5

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.1592. Min Act: -0.1700

Data Index: 5206241 (Open Web Text)

Max Activating Token Index: 62

Text #6

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.1433. Min Act: -0.1700

Data Index: 3963965 (Open Web Text)

Max Activating Token Index: 579

Text #7

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.1280. Min Act: -0.1700

Data Index: 892507 (Open Web Text)

Max Activating Token Index: 410

Text #8

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.1180. Min Act: -0.1700

Data Index: 165658 (Open Web Text)

Max Activating Token Index: 165

Text #9

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.0952. Min Act: -0.1700

Data Index: 7814271 (Open Web Text)

Max Activating Token Index: 311

Text #10

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.1076. Min Act: -0.1700

Data Index: 6692174 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.0806. Min Act: -0.1700

Data Index: 2598883 (Open Web Text)

Max Activating Token Index: 475

Text #12

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.0897. Min Act: -0.1700

Data Index: 8494909 (Open Web Text)

Max Activating Token Index: 357

Text #13

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.0802. Min Act: -0.1700

Data Index: 3672540 (Open Web Text)

Max Activating Token Index: 263

Text #14

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.0818. Min Act: -0.1700

Data Index: 2243498 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.0789. Min Act: -0.1700

Data Index: 6155773 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.0950. Min Act: -0.1700

Data Index: 3140345 (Open Web Text)

Max Activating Token Index: 917

Text #17

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.0873. Min Act: -0.1700

Data Index: 1441252 (Open Web Text)

Max Activating Token Index: 104

Text #18

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.0863. Min Act: -0.1696

Data Index: 5084856 (Open Web Text)

Max Activating Token Index: 532

Text #19

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.0783. Min Act: -0.1700

Data Index: 428848 (Open Web Text)

Max Activating Token Index: 57