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

Dataset: Open Web Text

Neuron 2650 in Layer 4

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: 3.3473. Min Range: -3.3473

Max Act: 3.3473. Min Act: -0.1700

Data Index: 7590762 (Open Web Text)

Max Activating Token Index: 33

Text #1

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.2804. Min Act: -0.1700

Data Index: 4083431 (Open Web Text)

Max Activating Token Index: 823

Text #2

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.1873. Min Act: -0.1700

Data Index: 39957 (Open Web Text)

Max Activating Token Index: 168

Text #3

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.1724. Min Act: -0.1700

Data Index: 6416432 (Open Web Text)

Max Activating Token Index: 640

Text #4

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.1481. Min Act: -0.1700

Data Index: 2781101 (Open Web Text)

Max Activating Token Index: 372

Text #5

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.1469. Min Act: -0.1700

Data Index: 5840381 (Open Web Text)

Max Activating Token Index: 679

Text #6

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.1115. Min Act: -0.1700

Data Index: 2902065 (Open Web Text)

Max Activating Token Index: 389

Text #7

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.1236. Min Act: -0.1700

Data Index: 8192608 (Open Web Text)

Max Activating Token Index: 471

Text #8

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.1247. Min Act: -0.1700

Data Index: 4155551 (Open Web Text)

Max Activating Token Index: 175

Text #9

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.1323. Min Act: -0.1700

Data Index: 3851408 (Open Web Text)

Max Activating Token Index: 173

Text #10

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.1208. Min Act: -0.1700

Data Index: 5493881 (Open Web Text)

Max Activating Token Index: 70

Text #11

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.1326. Min Act: -0.1700

Data Index: 5769667 (Open Web Text)

Max Activating Token Index: 401

Text #12

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.0921. Min Act: -0.1700

Data Index: 6623458 (Open Web Text)

Max Activating Token Index: 51

Text #13

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.0718. Min Act: -0.1700

Data Index: 5889292 (Open Web Text)

Max Activating Token Index: 869

Text #14

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.0876. Min Act: -0.1700

Data Index: 5051909 (Open Web Text)

Max Activating Token Index: 273

Text #15

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.1265. Min Act: -0.1700

Data Index: 8100814 (Open Web Text)

Max Activating Token Index: 466

Text #16

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.0996. Min Act: -0.1700

Data Index: 3570131 (Open Web Text)

Max Activating Token Index: 273

Text #17

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.0610. Min Act: -0.1700

Data Index: 2806634 (Open Web Text)

Max Activating Token Index: 505

Text #18

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.0686. Min Act: -0.1700

Data Index: 1149144 (Open Web Text)

Max Activating Token Index: 407

Text #19

Max Range: 3.3473. Min Range: -3.3473

Max Act: 3.0760. Min Act: -0.1700

Data Index: 1174649 (Open Web Text)

Max Activating Token Index: 479