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

Dataset: Open Web Text

Neuron 34 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: 4.5307. Min Range: -4.5307

Max Act: 4.5307. Min Act: -0.1700

Data Index: 4387397 (Open Web Text)

Max Activating Token Index: 776

Text #1

Max Range: 4.5307. Min Range: -4.5307

Max Act: 4.4802. Min Act: -0.1700

Data Index: 6155373 (Open Web Text)

Max Activating Token Index: 615

Text #2

Max Range: 4.5307. Min Range: -4.5307

Max Act: 4.4488. Min Act: -0.1700

Data Index: 3893403 (Open Web Text)

Max Activating Token Index: 937

Text #3

Max Range: 4.5307. Min Range: -4.5307

Max Act: 4.3932. Min Act: -0.1700

Data Index: 3893853 (Open Web Text)

Max Activating Token Index: 827

Text #4

Max Range: 4.5307. Min Range: -4.5307

Max Act: 4.4364. Min Act: -0.1700

Data Index: 5695092 (Open Web Text)

Max Activating Token Index: 382

Text #5

Max Range: 4.5307. Min Range: -4.5307

Max Act: 4.4255. Min Act: -0.1700

Data Index: 2017740 (Open Web Text)

Max Activating Token Index: 294

Text #6

Max Range: 4.5307. Min Range: -4.5307

Max Act: 4.4362. Min Act: -0.1700

Data Index: 3034773 (Open Web Text)

Max Activating Token Index: 872

Text #7

Max Range: 4.5307. Min Range: -4.5307

Max Act: 4.4130. Min Act: -0.1700

Data Index: 5092218 (Open Web Text)

Max Activating Token Index: 936

Text #8

Max Range: 4.5307. Min Range: -4.5307

Max Act: 4.3715. Min Act: -0.1700

Data Index: 5357688 (Open Web Text)

Max Activating Token Index: 441

Text #9

Max Range: 4.5307. Min Range: -4.5307

Max Act: 4.3953. Min Act: -0.1700

Data Index: 1200931 (Open Web Text)

Max Activating Token Index: 597

Text #10

Max Range: 4.5307. Min Range: -4.5307

Max Act: 4.3938. Min Act: -0.1700

Data Index: 8078263 (Open Web Text)

Max Activating Token Index: 738

Text #11

Max Range: 4.5307. Min Range: -4.5307

Max Act: 4.3897. Min Act: -0.1700

Data Index: 1405004 (Open Web Text)

Max Activating Token Index: 755

Text #12

Max Range: 4.5307. Min Range: -4.5307

Max Act: 4.3981. Min Act: -0.1700

Data Index: 7243674 (Open Web Text)

Max Activating Token Index: 608

Text #13

Max Range: 4.5307. Min Range: -4.5307

Max Act: 4.3580. Min Act: -0.1700

Data Index: 1136069 (Open Web Text)

Max Activating Token Index: 520

Text #14

Max Range: 4.5307. Min Range: -4.5307

Max Act: 4.3922. Min Act: -0.1700

Data Index: 6924326 (Open Web Text)

Max Activating Token Index: 952

Text #15

Max Range: 4.5307. Min Range: -4.5307

Max Act: 4.3847. Min Act: -0.1700

Data Index: 443466 (Open Web Text)

Max Activating Token Index: 1015

Text #16

Max Range: 4.5307. Min Range: -4.5307

Max Act: 4.3727. Min Act: -0.1700

Data Index: 6320301 (Open Web Text)

Max Activating Token Index: 815

Text #17

Max Range: 4.5307. Min Range: -4.5307

Max Act: 4.3424. Min Act: -0.1700

Data Index: 5338291 (Open Web Text)

Max Activating Token Index: 752

Text #18

Max Range: 4.5307. Min Range: -4.5307

Max Act: 4.3724. Min Act: -0.1700

Data Index: 1283156 (Open Web Text)

Max Activating Token Index: 274

Text #19

Max Range: 4.5307. Min Range: -4.5307

Max Act: 4.3340. Min Act: -0.1700

Data Index: 3921779 (Open Web Text)

Max Activating Token Index: 620