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

Dataset: Open Web Text

Neuron 2204 in Layer 1

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: 1.8599. Min Range: -1.8599

Max Act: 1.8599. Min Act: -0.1700

Data Index: 4675756 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.8035. Min Act: -0.1700

Data Index: 8733690 (Open Web Text)

Max Activating Token Index: 229

Text #2

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7916. Min Act: -0.1700

Data Index: 4377400 (Open Web Text)

Max Activating Token Index: 36

Text #3

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7852. Min Act: -0.1700

Data Index: 5651492 (Open Web Text)

Max Activating Token Index: 543

Text #4

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7749. Min Act: -0.1700

Data Index: 4675754 (Open Web Text)

Max Activating Token Index: 965

Text #5

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7820. Min Act: -0.1700

Data Index: 6673191 (Open Web Text)

Max Activating Token Index: 756

Text #6

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7750. Min Act: -0.1699

Data Index: 7771749 (Open Web Text)

Max Activating Token Index: 157

Text #7

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7632. Min Act: -0.1692

Data Index: 582732 (Open Web Text)

Max Activating Token Index: 170

Text #8

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7675. Min Act: -0.1699

Data Index: 8327195 (Open Web Text)

Max Activating Token Index: 480

Text #9

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7593. Min Act: -0.1656

Data Index: 8361537 (Open Web Text)

Max Activating Token Index: 1016

Text #10

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7585. Min Act: -0.1695

Data Index: 2840224 (Open Web Text)

Max Activating Token Index: 611

Text #11

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7539. Min Act: -0.1693

Data Index: 8823126 (Open Web Text)

Max Activating Token Index: 614

Text #12

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7514. Min Act: -0.1699

Data Index: 2926581 (Open Web Text)

Max Activating Token Index: 419

Text #13

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7438. Min Act: -0.1698

Data Index: 5169527 (Open Web Text)

Max Activating Token Index: 258

Text #14

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7503. Min Act: -0.1700

Data Index: 546379 (Open Web Text)

Max Activating Token Index: 1019

Text #15

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7421. Min Act: -0.1698

Data Index: 8082160 (Open Web Text)

Max Activating Token Index: 485

Text #16

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7340. Min Act: -0.1700

Data Index: 6163521 (Open Web Text)

Max Activating Token Index: 508

Text #17

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7340. Min Act: -0.1700

Data Index: 8742291 (Open Web Text)

Max Activating Token Index: 429

Text #18

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7261. Min Act: -0.1700

Data Index: 4875844 (Open Web Text)

Max Activating Token Index: 20

Text #19

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7323. Min Act: -0.1700

Data Index: 5319974 (Open Web Text)

Max Activating Token Index: 624