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

Dataset: Open Web Text

Neuron 1083 in Layer 4

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: 3.6420. Min Range: -3.6420

Max Act: 3.6390. Min Act: -0.1700

Data Index: 6598749 (Open Web Text)

Max Activating Token Index: 546

Text #1

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.6420. Min Act: -0.1700

Data Index: 8290892 (Open Web Text)

Max Activating Token Index: 726

Text #2

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5528. Min Act: -0.1700

Data Index: 978693 (Open Web Text)

Max Activating Token Index: 570

Text #3

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5880. Min Act: -0.1700

Data Index: 7433369 (Open Web Text)

Max Activating Token Index: 772

Text #4

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5785. Min Act: -0.1700

Data Index: 4702513 (Open Web Text)

Max Activating Token Index: 795

Text #5

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5234. Min Act: -0.1700

Data Index: 1572856 (Open Web Text)

Max Activating Token Index: 554

Text #6

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5509. Min Act: -0.1700

Data Index: 5063837 (Open Web Text)

Max Activating Token Index: 23

Text #7

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5044. Min Act: -0.1700

Data Index: 3830217 (Open Web Text)

Max Activating Token Index: 98

Text #8

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5675. Min Act: -0.1700

Data Index: 7114343 (Open Web Text)

Max Activating Token Index: 691

Text #9

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5135. Min Act: -0.1700

Data Index: 2489513 (Open Web Text)

Max Activating Token Index: 344

Text #10

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5236. Min Act: -0.1700

Data Index: 255750 (Open Web Text)

Max Activating Token Index: 585

Text #11

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5449. Min Act: -0.1700

Data Index: 5715642 (Open Web Text)

Max Activating Token Index: 663

Text #12

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5716. Min Act: -0.1700

Data Index: 5880013 (Open Web Text)

Max Activating Token Index: 88

Text #13

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5461. Min Act: -0.1700

Data Index: 8605844 (Open Web Text)

Max Activating Token Index: 333

Text #14

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5146. Min Act: -0.1700

Data Index: 4144583 (Open Web Text)

Max Activating Token Index: 293

Text #15

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5166. Min Act: -0.1700

Data Index: 7405108 (Open Web Text)

Max Activating Token Index: 494

Text #16

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.4827. Min Act: -0.1700

Data Index: 7717112 (Open Web Text)

Max Activating Token Index: 560

Text #17

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.4706. Min Act: -0.1700

Data Index: 8529658 (Open Web Text)

Max Activating Token Index: 586

Text #18

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.4876. Min Act: -0.1700

Data Index: 566964 (Open Web Text)

Max Activating Token Index: 655

Text #19

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.4960. Min Act: -0.1700

Data Index: 1072124 (Open Web Text)

Max Activating Token Index: 60