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

Dataset: Open Web Text

Neuron 1727 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: 5.9573. Min Range: -5.9573

Max Act: 5.9573. Min Act: -0.1700

Data Index: 349155 (Open Web Text)

Max Activating Token Index: 122

Text #1

Max Range: 5.9573. Min Range: -5.9573

Max Act: 5.5932. Min Act: -0.1700

Data Index: 789238 (Open Web Text)

Max Activating Token Index: 498

Text #2

Max Range: 5.9573. Min Range: -5.9573

Max Act: 5.5684. Min Act: -0.1700

Data Index: 8656251 (Open Web Text)

Max Activating Token Index: 152

Text #3

Max Range: 5.9573. Min Range: -5.9573

Max Act: 5.5823. Min Act: -0.1700

Data Index: 8239367 (Open Web Text)

Max Activating Token Index: 22

Text #4

Max Range: 5.9573. Min Range: -5.9573

Max Act: 5.5273. Min Act: -0.1700

Data Index: 5395852 (Open Web Text)

Max Activating Token Index: 310

Text #5

Max Range: 5.9573. Min Range: -5.9573

Max Act: 5.5122. Min Act: -0.1700

Data Index: 5395853 (Open Web Text)

Max Activating Token Index: 155

Text #6

Max Range: 5.9573. Min Range: -5.9573

Max Act: 5.5316. Min Act: -0.1700

Data Index: 3955100 (Open Web Text)

Max Activating Token Index: 787

Text #7

Max Range: 5.9573. Min Range: -5.9573

Max Act: 5.5310. Min Act: -0.1700

Data Index: 3012519 (Open Web Text)

Max Activating Token Index: 261

Text #8

Max Range: 5.9573. Min Range: -5.9573

Max Act: 5.5337. Min Act: -0.1700

Data Index: 2025723 (Open Web Text)

Max Activating Token Index: 85

Text #9

Max Range: 5.9573. Min Range: -5.9573

Max Act: 5.5166. Min Act: -0.1700

Data Index: 8195281 (Open Web Text)

Max Activating Token Index: 426

Text #10

Max Range: 5.9573. Min Range: -5.9573

Max Act: 5.5010. Min Act: -0.1700

Data Index: 1232152 (Open Web Text)

Max Activating Token Index: 775

Text #11

Max Range: 5.9573. Min Range: -5.9573

Max Act: 5.5033. Min Act: -0.1700

Data Index: 4702004 (Open Web Text)

Max Activating Token Index: 172

Text #12

Max Range: 5.9573. Min Range: -5.9573

Max Act: 5.4476. Min Act: -0.1700

Data Index: 5308015 (Open Web Text)

Max Activating Token Index: 226

Text #13

Max Range: 5.9573. Min Range: -5.9573

Max Act: 5.3976. Min Act: -0.1700

Data Index: 7686440 (Open Web Text)

Max Activating Token Index: 112

Text #14

Max Range: 5.9573. Min Range: -5.9573

Max Act: 5.3849. Min Act: -0.1700

Data Index: 3246120 (Open Web Text)

Max Activating Token Index: 261

Text #15

Max Range: 5.9573. Min Range: -5.9573

Max Act: 5.4000. Min Act: -0.1700

Data Index: 5372728 (Open Web Text)

Max Activating Token Index: 375

Text #16

Max Range: 5.9573. Min Range: -5.9573

Max Act: 5.3633. Min Act: -0.1700

Data Index: 332558 (Open Web Text)

Max Activating Token Index: 85

Text #17

Max Range: 5.9573. Min Range: -5.9573

Max Act: 5.4119. Min Act: -0.1700

Data Index: 7895519 (Open Web Text)

Max Activating Token Index: 637

Text #18

Max Range: 5.9573. Min Range: -5.9573

Max Act: 5.3947. Min Act: -0.1700

Data Index: 3563212 (Open Web Text)

Max Activating Token Index: 646

Text #19

Max Range: 5.9573. Min Range: -5.9573

Max Act: 5.3623. Min Act: -0.1700

Data Index: 110914 (Open Web Text)

Max Activating Token Index: 196