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

Dataset: Open Web Text

Neuron 157 in Layer 4

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: 3.7040. Min Range: -3.7040

Max Act: 3.7040. Min Act: -0.1700

Data Index: 2532554 (Open Web Text)

Max Activating Token Index: 434

Text #1

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.5910. Min Act: -0.1700

Data Index: 206126 (Open Web Text)

Max Activating Token Index: 971

Text #2

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.5511. Min Act: -0.1700

Data Index: 5555262 (Open Web Text)

Max Activating Token Index: 978

Text #3

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.5271. Min Act: -0.1700

Data Index: 1662227 (Open Web Text)

Max Activating Token Index: 554

Text #4

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.4946. Min Act: -0.1700

Data Index: 757622 (Open Web Text)

Max Activating Token Index: 671

Text #5

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.4738. Min Act: -0.1700

Data Index: 5745191 (Open Web Text)

Max Activating Token Index: 369

Text #6

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.4680. Min Act: -0.1700

Data Index: 4532296 (Open Web Text)

Max Activating Token Index: 359

Text #7

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.4271. Min Act: -0.1700

Data Index: 6820721 (Open Web Text)

Max Activating Token Index: 414

Text #8

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.4787. Min Act: -0.1700

Data Index: 3050432 (Open Web Text)

Max Activating Token Index: 676

Text #9

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.4622. Min Act: -0.1700

Data Index: 4473870 (Open Web Text)

Max Activating Token Index: 597

Text #10

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.4810. Min Act: -0.1700

Data Index: 6202391 (Open Web Text)

Max Activating Token Index: 102

Text #11

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.4801. Min Act: -0.1700

Data Index: 1032457 (Open Web Text)

Max Activating Token Index: 798

Text #12

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.4453. Min Act: -0.1700

Data Index: 2933301 (Open Web Text)

Max Activating Token Index: 856

Text #13

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.4526. Min Act: -0.1700

Data Index: 2814807 (Open Web Text)

Max Activating Token Index: 578

Text #14

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.4382. Min Act: -0.1700

Data Index: 345364 (Open Web Text)

Max Activating Token Index: 809

Text #15

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.4340. Min Act: -0.1700

Data Index: 1773473 (Open Web Text)

Max Activating Token Index: 81

Text #16

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.4120. Min Act: -0.1700

Data Index: 5829083 (Open Web Text)

Max Activating Token Index: 385

Text #17

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.4170. Min Act: -0.1700

Data Index: 2829045 (Open Web Text)

Max Activating Token Index: 414

Text #18

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.3854. Min Act: -0.1700

Data Index: 1180534 (Open Web Text)

Max Activating Token Index: 548

Text #19

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.4128. Min Act: -0.1700

Data Index: 654372 (Open Web Text)

Max Activating Token Index: 640