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

Dataset: Open Web Text

Neuron 316 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: 6.4923. Min Range: -6.4923

Max Act: 6.4923. Min Act: -0.1700

Data Index: 7940374 (Open Web Text)

Max Activating Token Index: 918

Text #1

Max Range: 6.4923. Min Range: -6.4923

Max Act: 6.3382. Min Act: -0.1700

Data Index: 3497304 (Open Web Text)

Max Activating Token Index: 563

Text #2

Max Range: 6.4923. Min Range: -6.4923

Max Act: 6.3530. Min Act: -0.1700

Data Index: 6653066 (Open Web Text)

Max Activating Token Index: 431

Text #3

Max Range: 6.4923. Min Range: -6.4923

Max Act: 6.3254. Min Act: -0.1700

Data Index: 7603813 (Open Web Text)

Max Activating Token Index: 505

Text #4

Max Range: 6.4923. Min Range: -6.4923

Max Act: 6.3092. Min Act: -0.1700

Data Index: 1665500 (Open Web Text)

Max Activating Token Index: 627

Text #5

Max Range: 6.4923. Min Range: -6.4923

Max Act: 6.2927. Min Act: -0.1700

Data Index: 5714882 (Open Web Text)

Max Activating Token Index: 330

Text #6

Max Range: 6.4923. Min Range: -6.4923

Max Act: 6.2597. Min Act: -0.1700

Data Index: 2791287 (Open Web Text)

Max Activating Token Index: 526

Text #7

Max Range: 6.4923. Min Range: -6.4923

Max Act: 6.2806. Min Act: -0.1700

Data Index: 250040 (Open Web Text)

Max Activating Token Index: 486

Text #8

Max Range: 6.4923. Min Range: -6.4923

Max Act: 6.2521. Min Act: -0.1700

Data Index: 8079129 (Open Web Text)

Max Activating Token Index: 176

Text #9

Max Range: 6.4923. Min Range: -6.4923

Max Act: 6.2675. Min Act: -0.1700

Data Index: 5697257 (Open Web Text)

Max Activating Token Index: 152

Text #10

Max Range: 6.4923. Min Range: -6.4923

Max Act: 6.2566. Min Act: -0.1700

Data Index: 5305476 (Open Web Text)

Max Activating Token Index: 646

Text #11

Max Range: 6.4923. Min Range: -6.4923

Max Act: 6.2030. Min Act: -0.1700

Data Index: 2135575 (Open Web Text)

Max Activating Token Index: 489

Text #12

Max Range: 6.4923. Min Range: -6.4923

Max Act: 6.1883. Min Act: -0.1700

Data Index: 4847917 (Open Web Text)

Max Activating Token Index: 318

Text #13

Max Range: 6.4923. Min Range: -6.4923

Max Act: 6.1650. Min Act: -0.1700

Data Index: 2053565 (Open Web Text)

Max Activating Token Index: 170

Text #14

Max Range: 6.4923. Min Range: -6.4923

Max Act: 6.1456. Min Act: -0.1700

Data Index: 5430114 (Open Web Text)

Max Activating Token Index: 699

Text #15

Max Range: 6.4923. Min Range: -6.4923

Max Act: 6.0952. Min Act: -0.1700

Data Index: 1868938 (Open Web Text)

Max Activating Token Index: 384

Text #16

Max Range: 6.4923. Min Range: -6.4923

Max Act: 6.1700. Min Act: -0.1700

Data Index: 1820211 (Open Web Text)

Max Activating Token Index: 1004

Text #17

Max Range: 6.4923. Min Range: -6.4923

Max Act: 6.1803. Min Act: -0.1700

Data Index: 4220843 (Open Web Text)

Max Activating Token Index: 349

Text #18

Max Range: 6.4923. Min Range: -6.4923

Max Act: 6.1580. Min Act: -0.1700

Data Index: 60185 (Open Web Text)

Max Activating Token Index: 376

Text #19

Max Range: 6.4923. Min Range: -6.4923

Max Act: 6.1343. Min Act: -0.1700

Data Index: 5503332 (Open Web Text)

Max Activating Token Index: 342