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

Dataset: Open Web Text

Neuron 1360 in Layer 6

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: 3.2428. Min Range: -3.2428

Max Act: 3.2428. Min Act: -0.1700

Data Index: 7804976 (Open Web Text)

Max Activating Token Index: 962

Text #1

Max Range: 3.2428. Min Range: -3.2428

Max Act: 3.2381. Min Act: -0.1700

Data Index: 836921 (Open Web Text)

Max Activating Token Index: 300

Text #2

Max Range: 3.2428. Min Range: -3.2428

Max Act: 3.1665. Min Act: -0.1700

Data Index: 7462033 (Open Web Text)

Max Activating Token Index: 403

Text #3

Max Range: 3.2428. Min Range: -3.2428

Max Act: 3.1534. Min Act: -0.1700

Data Index: 7368740 (Open Web Text)

Max Activating Token Index: 259

Text #4

Max Range: 3.2428. Min Range: -3.2428

Max Act: 3.0108. Min Act: -0.1700

Data Index: 3452885 (Open Web Text)

Max Activating Token Index: 743

Text #5

Max Range: 3.2428. Min Range: -3.2428

Max Act: 3.0011. Min Act: -0.1700

Data Index: 7839025 (Open Web Text)

Max Activating Token Index: 237

Text #6

Max Range: 3.2428. Min Range: -3.2428

Max Act: 2.9254. Min Act: -0.1700

Data Index: 7001927 (Open Web Text)

Max Activating Token Index: 998

Text #7

Max Range: 3.2428. Min Range: -3.2428

Max Act: 2.8262. Min Act: -0.1700

Data Index: 7098224 (Open Web Text)

Max Activating Token Index: 476

Text #8

Max Range: 3.2428. Min Range: -3.2428

Max Act: 2.8143. Min Act: -0.1700

Data Index: 571520 (Open Web Text)

Max Activating Token Index: 294

Text #9

Max Range: 3.2428. Min Range: -3.2428

Max Act: 2.7979. Min Act: -0.1700

Data Index: 8071214 (Open Web Text)

Max Activating Token Index: 937

Text #10

Max Range: 3.2428. Min Range: -3.2428

Max Act: 2.7730. Min Act: -0.1700

Data Index: 78002 (Open Web Text)

Max Activating Token Index: 777

Text #11

Max Range: 3.2428. Min Range: -3.2428

Max Act: 2.7783. Min Act: -0.1700

Data Index: 223530 (Open Web Text)

Max Activating Token Index: 844

Text #12

Max Range: 3.2428. Min Range: -3.2428

Max Act: 2.7808. Min Act: -0.1700

Data Index: 897696 (Open Web Text)

Max Activating Token Index: 57

Text #13

Max Range: 3.2428. Min Range: -3.2428

Max Act: 2.7619. Min Act: -0.1700

Data Index: 6004114 (Open Web Text)

Max Activating Token Index: 317

Text #14

Max Range: 3.2428. Min Range: -3.2428

Max Act: 2.7299. Min Act: -0.1700

Data Index: 2018502 (Open Web Text)

Max Activating Token Index: 408

Text #15

Max Range: 3.2428. Min Range: -3.2428

Max Act: 2.7603. Min Act: -0.1700

Data Index: 8242130 (Open Web Text)

Max Activating Token Index: 224

Text #16

Max Range: 3.2428. Min Range: -3.2428

Max Act: 2.7291. Min Act: -0.1700

Data Index: 6490514 (Open Web Text)

Max Activating Token Index: 290

Text #17

Max Range: 3.2428. Min Range: -3.2428

Max Act: 2.7458. Min Act: -0.1700

Data Index: 1245315 (Open Web Text)

Max Activating Token Index: 656

Text #18

Max Range: 3.2428. Min Range: -3.2428

Max Act: 2.7369. Min Act: -0.1700

Data Index: 6894002 (Open Web Text)

Max Activating Token Index: 816

Text #19

Max Range: 3.2428. Min Range: -3.2428

Max Act: 2.7361. Min Act: -0.1700

Data Index: 6569132 (Open Web Text)

Max Activating Token Index: 679