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

Dataset: Open Web Text

Neuron 2563 in Layer 2

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: 4.4376. Min Range: -4.4376

Max Act: 4.4376. Min Act: -0.1700

Data Index: 3933799 (Open Web Text)

Max Activating Token Index: 249

Text #1

Max Range: 4.4376. Min Range: -4.4376

Max Act: 4.3362. Min Act: -0.1700

Data Index: 469079 (Open Web Text)

Max Activating Token Index: 723

Text #2

Max Range: 4.4376. Min Range: -4.4376

Max Act: 4.3161. Min Act: -0.1700

Data Index: 251806 (Open Web Text)

Max Activating Token Index: 129

Text #3

Max Range: 4.4376. Min Range: -4.4376

Max Act: 4.3182. Min Act: -0.1700

Data Index: 17030 (Open Web Text)

Max Activating Token Index: 751

Text #4

Max Range: 4.4376. Min Range: -4.4376

Max Act: 4.3356. Min Act: -0.1700

Data Index: 2442410 (Open Web Text)

Max Activating Token Index: 333

Text #5

Max Range: 4.4376. Min Range: -4.4376

Max Act: 4.2550. Min Act: -0.1700

Data Index: 7338867 (Open Web Text)

Max Activating Token Index: 60

Text #6

Max Range: 4.4376. Min Range: -4.4376

Max Act: 4.2516. Min Act: -0.1700

Data Index: 4586125 (Open Web Text)

Max Activating Token Index: 38

Text #7

Max Range: 4.4376. Min Range: -4.4376

Max Act: 4.2545. Min Act: -0.1700

Data Index: 6440547 (Open Web Text)

Max Activating Token Index: 908

Text #8

Max Range: 4.4376. Min Range: -4.4376

Max Act: 4.2389. Min Act: -0.1700

Data Index: 2592578 (Open Web Text)

Max Activating Token Index: 386

Text #9

Max Range: 4.4376. Min Range: -4.4376

Max Act: 4.1933. Min Act: -0.1700

Data Index: 718135 (Open Web Text)

Max Activating Token Index: 215

Text #10

Max Range: 4.4376. Min Range: -4.4376

Max Act: 4.2071. Min Act: -0.1700

Data Index: 3732814 (Open Web Text)

Max Activating Token Index: 38

Text #11

Max Range: 4.4376. Min Range: -4.4376

Max Act: 4.2339. Min Act: -0.1700

Data Index: 5141043 (Open Web Text)

Max Activating Token Index: 111

Text #12

Max Range: 4.4376. Min Range: -4.4376

Max Act: 4.2357. Min Act: -0.1700

Data Index: 6295864 (Open Web Text)

Max Activating Token Index: 871

Text #13

Max Range: 4.4376. Min Range: -4.4376

Max Act: 4.2116. Min Act: -0.1700

Data Index: 4258880 (Open Web Text)

Max Activating Token Index: 64

Text #14

Max Range: 4.4376. Min Range: -4.4376

Max Act: 4.2058. Min Act: -0.1700

Data Index: 8010319 (Open Web Text)

Max Activating Token Index: 27

Text #15

Max Range: 4.4376. Min Range: -4.4376

Max Act: 4.2045. Min Act: -0.1700

Data Index: 1019838 (Open Web Text)

Max Activating Token Index: 52

Text #16

Max Range: 4.4376. Min Range: -4.4376

Max Act: 4.1718. Min Act: -0.1700

Data Index: 7395069 (Open Web Text)

Max Activating Token Index: 22

Text #17

Max Range: 4.4376. Min Range: -4.4376

Max Act: 4.2020. Min Act: -0.1700

Data Index: 5120712 (Open Web Text)

Max Activating Token Index: 122

Text #18

Max Range: 4.4376. Min Range: -4.4376

Max Act: 4.1770. Min Act: -0.1700

Data Index: 1292955 (Open Web Text)

Max Activating Token Index: 215

Text #19

Max Range: 4.4376. Min Range: -4.4376

Max Act: 4.1954. Min Act: -0.1700

Data Index: 1154457 (Open Web Text)

Max Activating Token Index: 272