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

Dataset: Open Web Text

Neuron 813 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: 3.2354. Min Range: -3.2354

Max Act: 3.2354. Min Act: -0.1700

Data Index: 7135175 (Open Web Text)

Max Activating Token Index: 520

Text #1

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.1582. Min Act: -0.1700

Data Index: 5187257 (Open Web Text)

Max Activating Token Index: 579

Text #2

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.1520. Min Act: -0.1700

Data Index: 6111787 (Open Web Text)

Max Activating Token Index: 404

Text #3

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.1465. Min Act: -0.1700

Data Index: 2207729 (Open Web Text)

Max Activating Token Index: 449

Text #4

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.1355. Min Act: -0.1700

Data Index: 5970373 (Open Web Text)

Max Activating Token Index: 537

Text #5

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0513. Min Act: -0.1700

Data Index: 7906283 (Open Web Text)

Max Activating Token Index: 224

Text #6

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0574. Min Act: -0.1700

Data Index: 2349769 (Open Web Text)

Max Activating Token Index: 423

Text #7

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0548. Min Act: -0.1700

Data Index: 3939492 (Open Web Text)

Max Activating Token Index: 374

Text #8

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0565. Min Act: -0.1700

Data Index: 4936125 (Open Web Text)

Max Activating Token Index: 394

Text #9

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0850. Min Act: -0.1700

Data Index: 7138927 (Open Web Text)

Max Activating Token Index: 886

Text #10

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0439. Min Act: -0.1700

Data Index: 157410 (Open Web Text)

Max Activating Token Index: 819

Text #11

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0214. Min Act: -0.1700

Data Index: 4500833 (Open Web Text)

Max Activating Token Index: 551

Text #12

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0334. Min Act: -0.1700

Data Index: 3300961 (Open Web Text)

Max Activating Token Index: 536

Text #13

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0160. Min Act: -0.1700

Data Index: 5474204 (Open Web Text)

Max Activating Token Index: 136

Text #14

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0244. Min Act: -0.1700

Data Index: 717359 (Open Web Text)

Max Activating Token Index: 411

Text #15

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0049. Min Act: -0.1700

Data Index: 1395283 (Open Web Text)

Max Activating Token Index: 163

Text #16

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0058. Min Act: -0.1700

Data Index: 1135066 (Open Web Text)

Max Activating Token Index: 504

Text #17

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0108. Min Act: -0.1700

Data Index: 900001 (Open Web Text)

Max Activating Token Index: 203

Text #18

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0267. Min Act: -0.1700

Data Index: 3897664 (Open Web Text)

Max Activating Token Index: 642

Text #19

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0360. Min Act: -0.1700

Data Index: 1937845 (Open Web Text)

Max Activating Token Index: 515