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

Dataset: Open Web Text

Neuron 384 in Layer 5

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: 4.7401. Min Range: -4.7401

Max Act: 4.7401. Min Act: -0.1700

Data Index: 7032797 (Open Web Text)

Max Activating Token Index: 94

Text #1

Max Range: 4.7401. Min Range: -4.7401

Max Act: 4.6902. Min Act: -0.1700

Data Index: 6893078 (Open Web Text)

Max Activating Token Index: 56

Text #2

Max Range: 4.7401. Min Range: -4.7401

Max Act: 4.6665. Min Act: -0.1700

Data Index: 804747 (Open Web Text)

Max Activating Token Index: 155

Text #3

Max Range: 4.7401. Min Range: -4.7401

Max Act: 4.6654. Min Act: -0.1700

Data Index: 4569491 (Open Web Text)

Max Activating Token Index: 392

Text #4

Max Range: 4.7401. Min Range: -4.7401

Max Act: 4.6166. Min Act: -0.1700

Data Index: 1462842 (Open Web Text)

Max Activating Token Index: 554

Text #5

Max Range: 4.7401. Min Range: -4.7401

Max Act: 4.5242. Min Act: -0.1700

Data Index: 1607799 (Open Web Text)

Max Activating Token Index: 149

Text #6

Max Range: 4.7401. Min Range: -4.7401

Max Act: 4.4928. Min Act: -0.1700

Data Index: 3842292 (Open Web Text)

Max Activating Token Index: 78

Text #7

Max Range: 4.7401. Min Range: -4.7401

Max Act: 4.5089. Min Act: -0.1700

Data Index: 6141823 (Open Web Text)

Max Activating Token Index: 500

Text #8

Max Range: 4.7401. Min Range: -4.7401

Max Act: 4.4700. Min Act: -0.1700

Data Index: 3680480 (Open Web Text)

Max Activating Token Index: 378

Text #9

Max Range: 4.7401. Min Range: -4.7401

Max Act: 4.4444. Min Act: -0.1700

Data Index: 2852854 (Open Web Text)

Max Activating Token Index: 115

Text #10

Max Range: 4.7401. Min Range: -4.7401

Max Act: 4.4632. Min Act: -0.1700

Data Index: 6877986 (Open Web Text)

Max Activating Token Index: 331

Text #11

Max Range: 4.7401. Min Range: -4.7401

Max Act: 4.4456. Min Act: -0.1700

Data Index: 8008340 (Open Web Text)

Max Activating Token Index: 147

Text #12

Max Range: 4.7401. Min Range: -4.7401

Max Act: 4.4357. Min Act: -0.1700

Data Index: 5623490 (Open Web Text)

Max Activating Token Index: 156

Text #13

Max Range: 4.7401. Min Range: -4.7401

Max Act: 4.4306. Min Act: -0.1700

Data Index: 4752067 (Open Web Text)

Max Activating Token Index: 488

Text #14

Max Range: 4.7401. Min Range: -4.7401

Max Act: 4.4525. Min Act: -0.1700

Data Index: 8366124 (Open Web Text)

Max Activating Token Index: 76

Text #15

Max Range: 4.7401. Min Range: -4.7401

Max Act: 4.4311. Min Act: -0.1700

Data Index: 7494426 (Open Web Text)

Max Activating Token Index: 569

Text #16

Max Range: 4.7401. Min Range: -4.7401

Max Act: 4.4041. Min Act: -0.1700

Data Index: 3893300 (Open Web Text)

Max Activating Token Index: 427

Text #17

Max Range: 4.7401. Min Range: -4.7401

Max Act: 4.3974. Min Act: -0.1700

Data Index: 1452363 (Open Web Text)

Max Activating Token Index: 183

Text #18

Max Range: 4.7401. Min Range: -4.7401

Max Act: 4.3954. Min Act: -0.1700

Data Index: 5514297 (Open Web Text)

Max Activating Token Index: 385

Text #19

Max Range: 4.7401. Min Range: -4.7401

Max Act: 4.4083. Min Act: -0.1700

Data Index: 4715175 (Open Web Text)

Max Activating Token Index: 151