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

Dataset: Open Web Text

Neuron 2402 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: 3.7783. Min Range: -3.7783

Max Act: 3.7783. Min Act: -0.1700

Data Index: 3628828 (Open Web Text)

Max Activating Token Index: 240

Text #1

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.7626. Min Act: -0.1700

Data Index: 2916274 (Open Web Text)

Max Activating Token Index: 195

Text #2

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.6899. Min Act: -0.1700

Data Index: 6992952 (Open Web Text)

Max Activating Token Index: 950

Text #3

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.6555. Min Act: -0.1700

Data Index: 8690025 (Open Web Text)

Max Activating Token Index: 815

Text #4

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.6409. Min Act: -0.1700

Data Index: 576276 (Open Web Text)

Max Activating Token Index: 359

Text #5

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.6093. Min Act: -0.1700

Data Index: 7181245 (Open Web Text)

Max Activating Token Index: 845

Text #6

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.6315. Min Act: -0.1700

Data Index: 3152625 (Open Web Text)

Max Activating Token Index: 241

Text #7

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.5742. Min Act: -0.1700

Data Index: 2810598 (Open Web Text)

Max Activating Token Index: 69

Text #8

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.5751. Min Act: -0.1700

Data Index: 4081308 (Open Web Text)

Max Activating Token Index: 392

Text #9

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.6022. Min Act: -0.1700

Data Index: 4374789 (Open Web Text)

Max Activating Token Index: 383

Text #10

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.5844. Min Act: -0.1700

Data Index: 1024097 (Open Web Text)

Max Activating Token Index: 275

Text #11

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.5693. Min Act: -0.1700

Data Index: 459739 (Open Web Text)

Max Activating Token Index: 475

Text #12

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.5601. Min Act: -0.1700

Data Index: 3929172 (Open Web Text)

Max Activating Token Index: 483

Text #13

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.5849. Min Act: -0.1700

Data Index: 7932126 (Open Web Text)

Max Activating Token Index: 982

Text #14

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.5855. Min Act: -0.1700

Data Index: 5960206 (Open Web Text)

Max Activating Token Index: 490

Text #15

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.5455. Min Act: -0.1700

Data Index: 3238024 (Open Web Text)

Max Activating Token Index: 383

Text #16

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.5313. Min Act: -0.1700

Data Index: 5194611 (Open Web Text)

Max Activating Token Index: 267

Text #17

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.5213. Min Act: -0.1700

Data Index: 5536806 (Open Web Text)

Max Activating Token Index: 208

Text #18

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.5393. Min Act: -0.1700

Data Index: 1289055 (Open Web Text)

Max Activating Token Index: 13

Text #19

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.5376. Min Act: -0.1700

Data Index: 6748472 (Open Web Text)

Max Activating Token Index: 784