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

Dataset: Open Web Text

Neuron 674 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: 3.6423. Min Range: -3.6423

Max Act: 3.6423. Min Act: -0.1700

Data Index: 4490424 (Open Web Text)

Max Activating Token Index: 565

Text #1

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.5834. Min Act: -0.1700

Data Index: 4490404 (Open Web Text)

Max Activating Token Index: 613

Text #2

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.4541. Min Act: -0.1700

Data Index: 4490410 (Open Web Text)

Max Activating Token Index: 337

Text #3

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.4235. Min Act: -0.1700

Data Index: 4490428 (Open Web Text)

Max Activating Token Index: 978

Text #4

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.4214. Min Act: -0.1700

Data Index: 2514153 (Open Web Text)

Max Activating Token Index: 438

Text #5

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.3775. Min Act: -0.1700

Data Index: 2865090 (Open Web Text)

Max Activating Token Index: 908

Text #6

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.3596. Min Act: -0.1700

Data Index: 6935796 (Open Web Text)

Max Activating Token Index: 591

Text #7

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.3405. Min Act: -0.1700

Data Index: 3760169 (Open Web Text)

Max Activating Token Index: 896

Text #8

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.3304. Min Act: -0.1700

Data Index: 2455627 (Open Web Text)

Max Activating Token Index: 276

Text #9

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.3328. Min Act: -0.1700

Data Index: 2107627 (Open Web Text)

Max Activating Token Index: 388

Text #10

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.3443. Min Act: -0.1700

Data Index: 2455623 (Open Web Text)

Max Activating Token Index: 351

Text #11

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.3331. Min Act: -0.1700

Data Index: 6935784 (Open Web Text)

Max Activating Token Index: 889

Text #12

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.3372. Min Act: -0.1700

Data Index: 4490408 (Open Web Text)

Max Activating Token Index: 300

Text #13

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.3082. Min Act: -0.1700

Data Index: 6729155 (Open Web Text)

Max Activating Token Index: 130

Text #14

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.2817. Min Act: -0.1700

Data Index: 4412598 (Open Web Text)

Max Activating Token Index: 156

Text #15

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.2921. Min Act: -0.1700

Data Index: 2514125 (Open Web Text)

Max Activating Token Index: 170

Text #16

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.3013. Min Act: -0.1700

Data Index: 5193581 (Open Web Text)

Max Activating Token Index: 333

Text #17

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.2587. Min Act: -0.1700

Data Index: 7335731 (Open Web Text)

Max Activating Token Index: 624

Text #18

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.2910. Min Act: -0.1700

Data Index: 2107626 (Open Web Text)

Max Activating Token Index: 527

Text #19

Max Range: 3.6423. Min Range: -3.6423

Max Act: 3.2889. Min Act: -0.1700

Data Index: 3760167 (Open Web Text)

Max Activating Token Index: 953