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

Dataset: Open Web Text

Neuron 2764 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: 3.9575. Min Range: -3.9575

Max Act: 3.9575. Min Act: -0.1700

Data Index: 2499292 (Open Web Text)

Max Activating Token Index: 696

Text #1

Max Range: 3.9575. Min Range: -3.9575

Max Act: 3.7943. Min Act: -0.1700

Data Index: 6128901 (Open Web Text)

Max Activating Token Index: 362

Text #2

Max Range: 3.9575. Min Range: -3.9575

Max Act: 3.7106. Min Act: -0.1700

Data Index: 6176161 (Open Web Text)

Max Activating Token Index: 264

Text #3

Max Range: 3.9575. Min Range: -3.9575

Max Act: 3.7319. Min Act: -0.1700

Data Index: 996247 (Open Web Text)

Max Activating Token Index: 741

Text #4

Max Range: 3.9575. Min Range: -3.9575

Max Act: 3.6932. Min Act: -0.1700

Data Index: 8084462 (Open Web Text)

Max Activating Token Index: 131

Text #5

Max Range: 3.9575. Min Range: -3.9575

Max Act: 3.6617. Min Act: -0.1700

Data Index: 7327877 (Open Web Text)

Max Activating Token Index: 855

Text #6

Max Range: 3.9575. Min Range: -3.9575

Max Act: 3.6589. Min Act: -0.1700

Data Index: 1741021 (Open Web Text)

Max Activating Token Index: 212

Text #7

Max Range: 3.9575. Min Range: -3.9575

Max Act: 3.6430. Min Act: -0.1700

Data Index: 3928054 (Open Web Text)

Max Activating Token Index: 383

Text #8

Max Range: 3.9575. Min Range: -3.9575

Max Act: 3.6355. Min Act: -0.1700

Data Index: 4471374 (Open Web Text)

Max Activating Token Index: 252

Text #9

Max Range: 3.9575. Min Range: -3.9575

Max Act: 3.5703. Min Act: -0.1700

Data Index: 5206019 (Open Web Text)

Max Activating Token Index: 867

Text #10

Max Range: 3.9575. Min Range: -3.9575

Max Act: 3.5993. Min Act: -0.1700

Data Index: 2463882 (Open Web Text)

Max Activating Token Index: 424

Text #11

Max Range: 3.9575. Min Range: -3.9575

Max Act: 3.5184. Min Act: -0.1700

Data Index: 6067649 (Open Web Text)

Max Activating Token Index: 164

Text #12

Max Range: 3.9575. Min Range: -3.9575

Max Act: 3.4892. Min Act: -0.1700

Data Index: 3996683 (Open Web Text)

Max Activating Token Index: 583

Text #13

Max Range: 3.9575. Min Range: -3.9575

Max Act: 3.5236. Min Act: -0.1700

Data Index: 7729345 (Open Web Text)

Max Activating Token Index: 777

Text #14

Max Range: 3.9575. Min Range: -3.9575

Max Act: 3.4618. Min Act: -0.1700

Data Index: 5706846 (Open Web Text)

Max Activating Token Index: 345

Text #15

Max Range: 3.9575. Min Range: -3.9575

Max Act: 3.4842. Min Act: -0.1700

Data Index: 6715048 (Open Web Text)

Max Activating Token Index: 850

Text #16

Max Range: 3.9575. Min Range: -3.9575

Max Act: 3.5156. Min Act: -0.1700

Data Index: 5539117 (Open Web Text)

Max Activating Token Index: 90

Text #17

Max Range: 3.9575. Min Range: -3.9575

Max Act: 3.4616. Min Act: -0.1700

Data Index: 2353764 (Open Web Text)

Max Activating Token Index: 595

Text #18

Max Range: 3.9575. Min Range: -3.9575

Max Act: 3.4766. Min Act: -0.1700

Data Index: 3656310 (Open Web Text)

Max Activating Token Index: 178

Text #19

Max Range: 3.9575. Min Range: -3.9575

Max Act: 3.4698. Min Act: -0.1700

Data Index: 6801453 (Open Web Text)

Max Activating Token Index: 378