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

Dataset: Open Web Text

Neuron 1661 in Layer 0

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: 1.8425. Min Range: -1.8425

Max Act: 1.8425. Min Act: -0.1700

Data Index: 4509163 (Open Web Text)

Max Activating Token Index: 233

Text #1

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.8307. Min Act: -0.1699

Data Index: 8342237 (Open Web Text)

Max Activating Token Index: 886

Text #2

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.8342. Min Act: -0.1686

Data Index: 1183044 (Open Web Text)

Max Activating Token Index: 19

Text #3

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.8216. Min Act: -0.1695

Data Index: 3660909 (Open Web Text)

Max Activating Token Index: 350

Text #4

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.8238. Min Act: -0.1693

Data Index: 221358 (Open Web Text)

Max Activating Token Index: 21

Text #5

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.8097. Min Act: -0.1687

Data Index: 4509162 (Open Web Text)

Max Activating Token Index: 967

Text #6

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.7962. Min Act: -0.1184

Data Index: 4230004 (Open Web Text)

Max Activating Token Index: 20

Text #7

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.7927. Min Act: -0.1464

Data Index: 8342241 (Open Web Text)

Max Activating Token Index: 692

Text #8

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.7909. Min Act: -0.1184

Data Index: 4230001 (Open Web Text)

Max Activating Token Index: 307

Text #9

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.7883. Min Act: -0.1695

Data Index: 937939 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.7885. Min Act: -0.1700

Data Index: 1468058 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.7868. Min Act: -0.1650

Data Index: 7391163 (Open Web Text)

Max Activating Token Index: 201

Text #12

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.7854. Min Act: -0.1699

Data Index: 525368 (Open Web Text)

Max Activating Token Index: 51

Text #13

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.7720. Min Act: -0.1700

Data Index: 6781802 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.7754. Min Act: -0.1699

Data Index: 3777509 (Open Web Text)

Max Activating Token Index: 393

Text #15

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.7805. Min Act: -0.1684

Data Index: 8072911 (Open Web Text)

Max Activating Token Index: 848

Text #16

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.7788. Min Act: -0.1700

Data Index: 2710407 (Open Web Text)

Max Activating Token Index: 23

Text #17

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.7797. Min Act: -0.1700

Data Index: 2756406 (Open Web Text)

Max Activating Token Index: 13

Text #18

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.7712. Min Act: -0.1688

Data Index: 2340184 (Open Web Text)

Max Activating Token Index: 28

Text #19

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.7719. Min Act: -0.1700

Data Index: 845586 (Open Web Text)

Max Activating Token Index: 14