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

Dataset: Open Web Text

Neuron 2465 in Layer 3

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: 4.4017. Min Range: -4.4017

Max Act: 4.3970. Min Act: -0.1700

Data Index: 6822746 (Open Web Text)

Max Activating Token Index: 166

Text #1

Max Range: 4.4017. Min Range: -4.4017

Max Act: 4.4017. Min Act: -0.1700

Data Index: 8672171 (Open Web Text)

Max Activating Token Index: 429

Text #2

Max Range: 4.4017. Min Range: -4.4017

Max Act: 4.1021. Min Act: -0.1700

Data Index: 1954635 (Open Web Text)

Max Activating Token Index: 425

Text #3

Max Range: 4.4017. Min Range: -4.4017

Max Act: 4.0579. Min Act: -0.1700

Data Index: 7993279 (Open Web Text)

Max Activating Token Index: 81

Text #4

Max Range: 4.4017. Min Range: -4.4017

Max Act: 4.0418. Min Act: -0.1700

Data Index: 6470751 (Open Web Text)

Max Activating Token Index: 461

Text #5

Max Range: 4.4017. Min Range: -4.4017

Max Act: 4.0205. Min Act: -0.1700

Data Index: 727993 (Open Web Text)

Max Activating Token Index: 167

Text #6

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.9770. Min Act: -0.1700

Data Index: 1494208 (Open Web Text)

Max Activating Token Index: 169

Text #7

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.9224. Min Act: -0.1700

Data Index: 6088941 (Open Web Text)

Max Activating Token Index: 222

Text #8

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.9440. Min Act: -0.1700

Data Index: 6168709 (Open Web Text)

Max Activating Token Index: 450

Text #9

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.9558. Min Act: -0.1700

Data Index: 2420722 (Open Web Text)

Max Activating Token Index: 521

Text #10

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.9838. Min Act: -0.1700

Data Index: 7645331 (Open Web Text)

Max Activating Token Index: 507

Text #11

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.9400. Min Act: -0.1700

Data Index: 8378075 (Open Web Text)

Max Activating Token Index: 559

Text #12

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.9214. Min Act: -0.1700

Data Index: 995395 (Open Web Text)

Max Activating Token Index: 393

Text #13

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.9211. Min Act: -0.1700

Data Index: 735555 (Open Web Text)

Max Activating Token Index: 665

Text #14

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.8618. Min Act: -0.1700

Data Index: 8676530 (Open Web Text)

Max Activating Token Index: 76

Text #15

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.9128. Min Act: -0.1700

Data Index: 7614465 (Open Web Text)

Max Activating Token Index: 927

Text #16

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.8692. Min Act: -0.1700

Data Index: 5837904 (Open Web Text)

Max Activating Token Index: 383

Text #17

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.8304. Min Act: -0.1700

Data Index: 3204379 (Open Web Text)

Max Activating Token Index: 79

Text #18

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.8528. Min Act: -0.1700

Data Index: 1745401 (Open Web Text)

Max Activating Token Index: 145

Text #19

Max Range: 4.4017. Min Range: -4.4017

Max Act: 3.8511. Min Act: -0.1700

Data Index: 2287319 (Open Web Text)

Max Activating Token Index: 922