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

Dataset: Open Web Text

Neuron 960 in Layer 2

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: 1.9033. Min Range: -1.9033

Max Act: 1.9033. Min Act: -0.1700

Data Index: 3553084 (Open Web Text)

Max Activating Token Index: 656

Text #1

Max Range: 1.9033. Min Range: -1.9033

Max Act: 1.8916. Min Act: -0.1700

Data Index: 5018357 (Open Web Text)

Max Activating Token Index: 489

Text #2

Max Range: 1.9033. Min Range: -1.9033

Max Act: 1.8770. Min Act: -0.1700

Data Index: 2115378 (Open Web Text)

Max Activating Token Index: 696

Text #3

Max Range: 1.9033. Min Range: -1.9033

Max Act: 1.8630. Min Act: -0.1700

Data Index: 5668268 (Open Web Text)

Max Activating Token Index: 700

Text #4

Max Range: 1.9033. Min Range: -1.9033

Max Act: 1.8855. Min Act: -0.1700

Data Index: 1928420 (Open Web Text)

Max Activating Token Index: 912

Text #5

Max Range: 1.9033. Min Range: -1.9033

Max Act: 1.8647. Min Act: -0.1700

Data Index: 2349972 (Open Web Text)

Max Activating Token Index: 518

Text #6

Max Range: 1.9033. Min Range: -1.9033

Max Act: 1.8486. Min Act: -0.1700

Data Index: 2829535 (Open Web Text)

Max Activating Token Index: 676

Text #7

Max Range: 1.9033. Min Range: -1.9033

Max Act: 1.8636. Min Act: -0.1700

Data Index: 3819787 (Open Web Text)

Max Activating Token Index: 415

Text #8

Max Range: 1.9033. Min Range: -1.9033

Max Act: 1.8437. Min Act: -0.1700

Data Index: 70920 (Open Web Text)

Max Activating Token Index: 888

Text #9

Max Range: 1.9033. Min Range: -1.9033

Max Act: 1.8613. Min Act: -0.1700

Data Index: 4644393 (Open Web Text)

Max Activating Token Index: 395

Text #10

Max Range: 1.9033. Min Range: -1.9033

Max Act: 1.8397. Min Act: -0.1700

Data Index: 2766413 (Open Web Text)

Max Activating Token Index: 610

Text #11

Max Range: 1.9033. Min Range: -1.9033

Max Act: 1.8361. Min Act: -0.1700

Data Index: 4441076 (Open Web Text)

Max Activating Token Index: 478

Text #12

Max Range: 1.9033. Min Range: -1.9033

Max Act: 1.8445. Min Act: -0.1700

Data Index: 2019264 (Open Web Text)

Max Activating Token Index: 572

Text #13

Max Range: 1.9033. Min Range: -1.9033

Max Act: 1.8212. Min Act: -0.1700

Data Index: 5144017 (Open Web Text)

Max Activating Token Index: 174

Text #14

Max Range: 1.9033. Min Range: -1.9033

Max Act: 1.8258. Min Act: -0.1700

Data Index: 8105923 (Open Web Text)

Max Activating Token Index: 85

Text #15

Max Range: 1.9033. Min Range: -1.9033

Max Act: 1.8174. Min Act: -0.1700

Data Index: 3252783 (Open Web Text)

Max Activating Token Index: 693

Text #16

Max Range: 1.9033. Min Range: -1.9033

Max Act: 1.8144. Min Act: -0.1700

Data Index: 6979165 (Open Web Text)

Max Activating Token Index: 992

Text #17

Max Range: 1.9033. Min Range: -1.9033

Max Act: 1.8183. Min Act: -0.1700

Data Index: 1493106 (Open Web Text)

Max Activating Token Index: 790

Text #18

Max Range: 1.9033. Min Range: -1.9033

Max Act: 1.8108. Min Act: -0.1700

Data Index: 6284084 (Open Web Text)

Max Activating Token Index: 560

Text #19

Max Range: 1.9033. Min Range: -1.9033

Max Act: 1.8114. Min Act: -0.1700

Data Index: 1928423 (Open Web Text)

Max Activating Token Index: 153