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

Dataset: Open Web Text

Neuron 2632 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: 3.9306. Min Range: -3.9306

Max Act: 3.9306. Min Act: -0.1700

Data Index: 4375504 (Open Web Text)

Max Activating Token Index: 777

Text #1

Max Range: 3.9306. Min Range: -3.9306

Max Act: 3.7631. Min Act: -0.1700

Data Index: 7363487 (Open Web Text)

Max Activating Token Index: 79

Text #2

Max Range: 3.9306. Min Range: -3.9306

Max Act: 3.7406. Min Act: -0.1700

Data Index: 1828170 (Open Web Text)

Max Activating Token Index: 128

Text #3

Max Range: 3.9306. Min Range: -3.9306

Max Act: 3.6985. Min Act: -0.1700

Data Index: 8173490 (Open Web Text)

Max Activating Token Index: 279

Text #4

Max Range: 3.9306. Min Range: -3.9306

Max Act: 3.5793. Min Act: -0.1700

Data Index: 1232793 (Open Web Text)

Max Activating Token Index: 719

Text #5

Max Range: 3.9306. Min Range: -3.9306

Max Act: 3.5816. Min Act: -0.1700

Data Index: 2305992 (Open Web Text)

Max Activating Token Index: 454

Text #6

Max Range: 3.9306. Min Range: -3.9306

Max Act: 3.5535. Min Act: -0.1700

Data Index: 2761953 (Open Web Text)

Max Activating Token Index: 237

Text #7

Max Range: 3.9306. Min Range: -3.9306

Max Act: 3.5097. Min Act: -0.1700

Data Index: 6631020 (Open Web Text)

Max Activating Token Index: 463

Text #8

Max Range: 3.9306. Min Range: -3.9306

Max Act: 3.4713. Min Act: -0.1700

Data Index: 7833779 (Open Web Text)

Max Activating Token Index: 1011

Text #9

Max Range: 3.9306. Min Range: -3.9306

Max Act: 3.4720. Min Act: -0.1700

Data Index: 3402475 (Open Web Text)

Max Activating Token Index: 775

Text #10

Max Range: 3.9306. Min Range: -3.9306

Max Act: 3.4733. Min Act: -0.1700

Data Index: 8540034 (Open Web Text)

Max Activating Token Index: 933

Text #11

Max Range: 3.9306. Min Range: -3.9306

Max Act: 3.4549. Min Act: -0.1700

Data Index: 3108249 (Open Web Text)

Max Activating Token Index: 260

Text #12

Max Range: 3.9306. Min Range: -3.9306

Max Act: 3.4655. Min Act: -0.1700

Data Index: 53243 (Open Web Text)

Max Activating Token Index: 719

Text #13

Max Range: 3.9306. Min Range: -3.9306

Max Act: 3.4507. Min Act: -0.1700

Data Index: 6330296 (Open Web Text)

Max Activating Token Index: 230

Text #14

Max Range: 3.9306. Min Range: -3.9306

Max Act: 3.4504. Min Act: -0.1700

Data Index: 1074169 (Open Web Text)

Max Activating Token Index: 668

Text #15

Max Range: 3.9306. Min Range: -3.9306

Max Act: 3.4247. Min Act: -0.1700

Data Index: 5749030 (Open Web Text)

Max Activating Token Index: 106

Text #16

Max Range: 3.9306. Min Range: -3.9306

Max Act: 3.3989. Min Act: -0.1700

Data Index: 3708837 (Open Web Text)

Max Activating Token Index: 503

Text #17

Max Range: 3.9306. Min Range: -3.9306

Max Act: 3.3978. Min Act: -0.1700

Data Index: 2730316 (Open Web Text)

Max Activating Token Index: 213

Text #18

Max Range: 3.9306. Min Range: -3.9306

Max Act: 3.4012. Min Act: -0.1700

Data Index: 1859486 (Open Web Text)

Max Activating Token Index: 596

Text #19

Max Range: 3.9306. Min Range: -3.9306

Max Act: 3.3884. Min Act: -0.1700

Data Index: 6429116 (Open Web Text)

Max Activating Token Index: 864