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

Dataset: Open Web Text

Neuron 2562 in Layer 5

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: 10.6439. Min Range: -10.6439

Max Act: 10.6439. Min Act: -0.1700

Data Index: 2726392 (Open Web Text)

Max Activating Token Index: 743

Text #1

Max Range: 10.6439. Min Range: -10.6439

Max Act: 10.5840. Min Act: -0.1700

Data Index: 3231500 (Open Web Text)

Max Activating Token Index: 866

Text #2

Max Range: 10.6439. Min Range: -10.6439

Max Act: 10.5186. Min Act: -0.1700

Data Index: 8784317 (Open Web Text)

Max Activating Token Index: 582

Text #3

Max Range: 10.6439. Min Range: -10.6439

Max Act: 10.4316. Min Act: -0.1700

Data Index: 6449521 (Open Web Text)

Max Activating Token Index: 664

Text #4

Max Range: 10.6439. Min Range: -10.6439

Max Act: 10.3443. Min Act: -0.1699

Data Index: 112247 (Open Web Text)

Max Activating Token Index: 543

Text #5

Max Range: 10.6439. Min Range: -10.6439

Max Act: 10.2886. Min Act: -0.1700

Data Index: 174717 (Open Web Text)

Max Activating Token Index: 223

Text #6

Max Range: 10.6439. Min Range: -10.6439

Max Act: 10.2490. Min Act: -0.1700

Data Index: 6598122 (Open Web Text)

Max Activating Token Index: 658

Text #7

Max Range: 10.6439. Min Range: -10.6439

Max Act: 10.2702. Min Act: -0.1695

Data Index: 622107 (Open Web Text)

Max Activating Token Index: 737

Text #8

Max Range: 10.6439. Min Range: -10.6439

Max Act: 10.2152. Min Act: -0.1700

Data Index: 4902145 (Open Web Text)

Max Activating Token Index: 79

Text #9

Max Range: 10.6439. Min Range: -10.6439

Max Act: 10.1680. Min Act: -0.1700

Data Index: 1180722 (Open Web Text)

Max Activating Token Index: 123

Text #10

Max Range: 10.6439. Min Range: -10.6439

Max Act: 10.1288. Min Act: -0.1700

Data Index: 1648348 (Open Web Text)

Max Activating Token Index: 825

Text #11

Max Range: 10.6439. Min Range: -10.6439

Max Act: 10.1815. Min Act: -0.1700

Data Index: 3802064 (Open Web Text)

Max Activating Token Index: 511

Text #12

Max Range: 10.6439. Min Range: -10.6439

Max Act: 10.0345. Min Act: -0.1700

Data Index: 2360243 (Open Web Text)

Max Activating Token Index: 61

Text #13

Max Range: 10.6439. Min Range: -10.6439

Max Act: 10.1280. Min Act: -0.1700

Data Index: 6947155 (Open Web Text)

Max Activating Token Index: 917

Text #14

Max Range: 10.6439. Min Range: -10.6439

Max Act: 10.0518. Min Act: -0.1700

Data Index: 7778865 (Open Web Text)

Max Activating Token Index: 840

Text #15

Max Range: 10.6439. Min Range: -10.6439

Max Act: 10.0726. Min Act: -0.1696

Data Index: 6540775 (Open Web Text)

Max Activating Token Index: 536

Text #16

Max Range: 10.6439. Min Range: -10.6439

Max Act: 10.0573. Min Act: -0.1700

Data Index: 7693489 (Open Web Text)

Max Activating Token Index: 325

Text #17

Max Range: 10.6439. Min Range: -10.6439

Max Act: 10.0731. Min Act: -0.1700

Data Index: 4366020 (Open Web Text)

Max Activating Token Index: 300

Text #18

Max Range: 10.6439. Min Range: -10.6439

Max Act: 10.0521. Min Act: -0.1700

Data Index: 2450307 (Open Web Text)

Max Activating Token Index: 960

Text #19

Max Range: 10.6439. Min Range: -10.6439

Max Act: 9.9899. Min Act: -0.1700

Data Index: 6270770 (Open Web Text)

Max Activating Token Index: 690