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

Dataset: Open Web Text

Neuron 2153 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: 5.1307. Min Range: -5.1307

Max Act: 5.1307. Min Act: -0.1700

Data Index: 6860288 (Open Web Text)

Max Activating Token Index: 416

Text #1

Max Range: 5.1307. Min Range: -5.1307

Max Act: 5.1050. Min Act: -0.1700

Data Index: 1930609 (Open Web Text)

Max Activating Token Index: 671

Text #2

Max Range: 5.1307. Min Range: -5.1307

Max Act: 5.0666. Min Act: -0.1700

Data Index: 5489088 (Open Web Text)

Max Activating Token Index: 231

Text #3

Max Range: 5.1307. Min Range: -5.1307

Max Act: 5.0193. Min Act: -0.1700

Data Index: 7295368 (Open Web Text)

Max Activating Token Index: 581

Text #4

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.9847. Min Act: -0.1700

Data Index: 4536488 (Open Web Text)

Max Activating Token Index: 914

Text #5

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.9790. Min Act: -0.1700

Data Index: 6519309 (Open Web Text)

Max Activating Token Index: 152

Text #6

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.9631. Min Act: -0.1700

Data Index: 1693545 (Open Web Text)

Max Activating Token Index: 101

Text #7

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.9475. Min Act: -0.1700

Data Index: 7495382 (Open Web Text)

Max Activating Token Index: 483

Text #8

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.8747. Min Act: -0.1700

Data Index: 4388812 (Open Web Text)

Max Activating Token Index: 695

Text #9

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.8864. Min Act: -0.1700

Data Index: 7098406 (Open Web Text)

Max Activating Token Index: 472

Text #10

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.8969. Min Act: -0.1700

Data Index: 1348271 (Open Web Text)

Max Activating Token Index: 525

Text #11

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.9080. Min Act: -0.1700

Data Index: 1854996 (Open Web Text)

Max Activating Token Index: 478

Text #12

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.8758. Min Act: -0.1700

Data Index: 2798551 (Open Web Text)

Max Activating Token Index: 734

Text #13

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.8695. Min Act: -0.1700

Data Index: 7036865 (Open Web Text)

Max Activating Token Index: 310

Text #14

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.8683. Min Act: -0.1700

Data Index: 4064754 (Open Web Text)

Max Activating Token Index: 56

Text #15

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.8538. Min Act: -0.1700

Data Index: 2927886 (Open Web Text)

Max Activating Token Index: 559

Text #16

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.8736. Min Act: -0.1700

Data Index: 1479486 (Open Web Text)

Max Activating Token Index: 696

Text #17

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.8674. Min Act: -0.1700

Data Index: 565287 (Open Web Text)

Max Activating Token Index: 277

Text #18

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.8140. Min Act: -0.1700

Data Index: 6950268 (Open Web Text)

Max Activating Token Index: 695

Text #19

Max Range: 5.1307. Min Range: -5.1307

Max Act: 4.8286. Min Act: -0.1700

Data Index: 4506216 (Open Web Text)

Max Activating Token Index: 301