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

Dataset: Open Web Text

Neuron 284 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: 7.5866. Min Range: -7.5866

Max Act: 7.5866. Min Act: -0.1700

Data Index: 1328147 (Open Web Text)

Max Activating Token Index: 359

Text #1

Max Range: 7.5866. Min Range: -7.5866

Max Act: 7.5152. Min Act: -0.1700

Data Index: 7443551 (Open Web Text)

Max Activating Token Index: 905

Text #2

Max Range: 7.5866. Min Range: -7.5866

Max Act: 7.4887. Min Act: -0.1700

Data Index: 1331995 (Open Web Text)

Max Activating Token Index: 233

Text #3

Max Range: 7.5866. Min Range: -7.5866

Max Act: 7.4135. Min Act: -0.1700

Data Index: 5057552 (Open Web Text)

Max Activating Token Index: 400

Text #4

Max Range: 7.5866. Min Range: -7.5866

Max Act: 7.3094. Min Act: -0.1700

Data Index: 2428058 (Open Web Text)

Max Activating Token Index: 670

Text #5

Max Range: 7.5866. Min Range: -7.5866

Max Act: 7.3129. Min Act: -0.1700

Data Index: 1993657 (Open Web Text)

Max Activating Token Index: 779

Text #6

Max Range: 7.5866. Min Range: -7.5866

Max Act: 7.3031. Min Act: -0.1700

Data Index: 4198850 (Open Web Text)

Max Activating Token Index: 596

Text #7

Max Range: 7.5866. Min Range: -7.5866

Max Act: 7.2628. Min Act: -0.1700

Data Index: 2492488 (Open Web Text)

Max Activating Token Index: 344

Text #8

Max Range: 7.5866. Min Range: -7.5866

Max Act: 7.1686. Min Act: -0.1700

Data Index: 5431453 (Open Web Text)

Max Activating Token Index: 411

Text #9

Max Range: 7.5866. Min Range: -7.5866

Max Act: 7.1556. Min Act: -0.1700

Data Index: 6283515 (Open Web Text)

Max Activating Token Index: 607

Text #10

Max Range: 7.5866. Min Range: -7.5866

Max Act: 7.2081. Min Act: -0.1700

Data Index: 6647824 (Open Web Text)

Max Activating Token Index: 186

Text #11

Max Range: 7.5866. Min Range: -7.5866

Max Act: 7.1666. Min Act: -0.1700

Data Index: 1368350 (Open Web Text)

Max Activating Token Index: 554

Text #12

Max Range: 7.5866. Min Range: -7.5866

Max Act: 7.1679. Min Act: -0.1700

Data Index: 6306733 (Open Web Text)

Max Activating Token Index: 211

Text #13

Max Range: 7.5866. Min Range: -7.5866

Max Act: 7.1725. Min Act: -0.1700

Data Index: 6794269 (Open Web Text)

Max Activating Token Index: 972

Text #14

Max Range: 7.5866. Min Range: -7.5866

Max Act: 7.1428. Min Act: -0.1700

Data Index: 3268759 (Open Web Text)

Max Activating Token Index: 334

Text #15

Max Range: 7.5866. Min Range: -7.5866

Max Act: 7.1698. Min Act: -0.1700

Data Index: 6958195 (Open Web Text)

Max Activating Token Index: 158

Text #16

Max Range: 7.5866. Min Range: -7.5866

Max Act: 7.1678. Min Act: -0.1700

Data Index: 3381190 (Open Web Text)

Max Activating Token Index: 540

Text #17

Max Range: 7.5866. Min Range: -7.5866

Max Act: 7.1977. Min Act: -0.1700

Data Index: 2649112 (Open Web Text)

Max Activating Token Index: 430

Text #18

Max Range: 7.5866. Min Range: -7.5866

Max Act: 7.1612. Min Act: -0.1700

Data Index: 4716910 (Open Web Text)

Max Activating Token Index: 153

Text #19

Max Range: 7.5866. Min Range: -7.5866

Max Act: 7.1215. Min Act: -0.1700

Data Index: 2955765 (Open Web Text)

Max Activating Token Index: 189