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

Dataset: Open Web Text

Neuron 436 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: 2.8487. Min Range: -2.8487

Max Act: 2.8487. Min Act: -0.1700

Data Index: 3705738 (Open Web Text)

Max Activating Token Index: 270

Text #1

Max Range: 2.8487. Min Range: -2.8487

Max Act: 2.8040. Min Act: -0.1700

Data Index: 6617023 (Open Web Text)

Max Activating Token Index: 171

Text #2

Max Range: 2.8487. Min Range: -2.8487

Max Act: 2.7497. Min Act: -0.1700

Data Index: 7301837 (Open Web Text)

Max Activating Token Index: 438

Text #3

Max Range: 2.8487. Min Range: -2.8487

Max Act: 2.7559. Min Act: -0.1700

Data Index: 3751401 (Open Web Text)

Max Activating Token Index: 378

Text #4

Max Range: 2.8487. Min Range: -2.8487

Max Act: 2.7346. Min Act: -0.1700

Data Index: 8458704 (Open Web Text)

Max Activating Token Index: 374

Text #5

Max Range: 2.8487. Min Range: -2.8487

Max Act: 2.7100. Min Act: -0.1700

Data Index: 8797936 (Open Web Text)

Max Activating Token Index: 349

Text #6

Max Range: 2.8487. Min Range: -2.8487

Max Act: 2.6803. Min Act: -0.1700

Data Index: 3114906 (Open Web Text)

Max Activating Token Index: 705

Text #7

Max Range: 2.8487. Min Range: -2.8487

Max Act: 2.6930. Min Act: -0.1700

Data Index: 1057107 (Open Web Text)

Max Activating Token Index: 447

Text #8

Max Range: 2.8487. Min Range: -2.8487

Max Act: 2.6333. Min Act: -0.1700

Data Index: 7810200 (Open Web Text)

Max Activating Token Index: 142

Text #9

Max Range: 2.8487. Min Range: -2.8487

Max Act: 2.6191. Min Act: -0.1700

Data Index: 2378599 (Open Web Text)

Max Activating Token Index: 362

Text #10

Max Range: 2.8487. Min Range: -2.8487

Max Act: 2.5978. Min Act: -0.1700

Data Index: 2091899 (Open Web Text)

Max Activating Token Index: 168

Text #11

Max Range: 2.8487. Min Range: -2.8487

Max Act: 2.6511. Min Act: -0.1700

Data Index: 2938600 (Open Web Text)

Max Activating Token Index: 824

Text #12

Max Range: 2.8487. Min Range: -2.8487

Max Act: 2.5991. Min Act: -0.1700

Data Index: 4033681 (Open Web Text)

Max Activating Token Index: 76

Text #13

Max Range: 2.8487. Min Range: -2.8487

Max Act: 2.5865. Min Act: -0.1700

Data Index: 3545276 (Open Web Text)

Max Activating Token Index: 374

Text #14

Max Range: 2.8487. Min Range: -2.8487

Max Act: 2.5691. Min Act: -0.1700

Data Index: 7926673 (Open Web Text)

Max Activating Token Index: 142

Text #15

Max Range: 2.8487. Min Range: -2.8487

Max Act: 2.5841. Min Act: -0.1700

Data Index: 7218514 (Open Web Text)

Max Activating Token Index: 910

Text #16

Max Range: 2.8487. Min Range: -2.8487

Max Act: 2.6162. Min Act: -0.1700

Data Index: 3290473 (Open Web Text)

Max Activating Token Index: 686

Text #17

Max Range: 2.8487. Min Range: -2.8487

Max Act: 2.5648. Min Act: -0.1700

Data Index: 186471 (Open Web Text)

Max Activating Token Index: 297

Text #18

Max Range: 2.8487. Min Range: -2.8487

Max Act: 2.5794. Min Act: -0.1700

Data Index: 3921972 (Open Web Text)

Max Activating Token Index: 630

Text #19

Max Range: 2.8487. Min Range: -2.8487

Max Act: 2.5610. Min Act: -0.1700

Data Index: 7371023 (Open Web Text)

Max Activating Token Index: 267