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

Dataset: Open Web Text

Neuron 2739 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: 4.4366. Min Range: -4.4366

Max Act: 4.4366. Min Act: -0.1700

Data Index: 2394441 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.4366. Min Range: -4.4366

Max Act: 4.3839. Min Act: -0.1700

Data Index: 8553188 (Open Web Text)

Max Activating Token Index: 242

Text #2

Max Range: 4.4366. Min Range: -4.4366

Max Act: 4.3716. Min Act: -0.1700

Data Index: 4781088 (Open Web Text)

Max Activating Token Index: 404

Text #3

Max Range: 4.4366. Min Range: -4.4366

Max Act: 4.3999. Min Act: -0.1700

Data Index: 8025235 (Open Web Text)

Max Activating Token Index: 435

Text #4

Max Range: 4.4366. Min Range: -4.4366

Max Act: 4.3420. Min Act: -0.1700

Data Index: 8796442 (Open Web Text)

Max Activating Token Index: 788

Text #5

Max Range: 4.4366. Min Range: -4.4366

Max Act: 4.2801. Min Act: -0.1700

Data Index: 6570271 (Open Web Text)

Max Activating Token Index: 366

Text #6

Max Range: 4.4366. Min Range: -4.4366

Max Act: 4.2913. Min Act: -0.1700

Data Index: 3385779 (Open Web Text)

Max Activating Token Index: 561

Text #7

Max Range: 4.4366. Min Range: -4.4366

Max Act: 4.2984. Min Act: -0.1700

Data Index: 5896939 (Open Web Text)

Max Activating Token Index: 274

Text #8

Max Range: 4.4366. Min Range: -4.4366

Max Act: 4.3204. Min Act: -0.1700

Data Index: 4222649 (Open Web Text)

Max Activating Token Index: 271

Text #9

Max Range: 4.4366. Min Range: -4.4366

Max Act: 4.2918. Min Act: -0.1700

Data Index: 2347689 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 4.4366. Min Range: -4.4366

Max Act: 4.2788. Min Act: -0.1700

Data Index: 6663066 (Open Web Text)

Max Activating Token Index: 583

Text #11

Max Range: 4.4366. Min Range: -4.4366

Max Act: 4.2493. Min Act: -0.1700

Data Index: 2883997 (Open Web Text)

Max Activating Token Index: 64

Text #12

Max Range: 4.4366. Min Range: -4.4366

Max Act: 4.2531. Min Act: -0.1700

Data Index: 5192085 (Open Web Text)

Max Activating Token Index: 444

Text #13

Max Range: 4.4366. Min Range: -4.4366

Max Act: 4.2679. Min Act: -0.1700

Data Index: 1085140 (Open Web Text)

Max Activating Token Index: 201

Text #14

Max Range: 4.4366. Min Range: -4.4366

Max Act: 4.2855. Min Act: -0.1700

Data Index: 4710410 (Open Web Text)

Max Activating Token Index: 618

Text #15

Max Range: 4.4366. Min Range: -4.4366

Max Act: 4.2250. Min Act: -0.1700

Data Index: 7492277 (Open Web Text)

Max Activating Token Index: 522

Text #16

Max Range: 4.4366. Min Range: -4.4366

Max Act: 4.2314. Min Act: -0.1700

Data Index: 826508 (Open Web Text)

Max Activating Token Index: 462

Text #17

Max Range: 4.4366. Min Range: -4.4366

Max Act: 4.2577. Min Act: -0.1700

Data Index: 5229697 (Open Web Text)

Max Activating Token Index: 24

Text #18

Max Range: 4.4366. Min Range: -4.4366

Max Act: 4.2324. Min Act: -0.1700

Data Index: 3541176 (Open Web Text)

Max Activating Token Index: 911

Text #19

Max Range: 4.4366. Min Range: -4.4366

Max Act: 4.2337. Min Act: -0.1700

Data Index: 3218421 (Open Web Text)

Max Activating Token Index: 667