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

Dataset: Open Web Text

Neuron 2017 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: 3.0430. Min Range: -3.0430

Max Act: 3.0430. Min Act: -0.1700

Data Index: 2803139 (Open Web Text)

Max Activating Token Index: 308

Text #1

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.9472. Min Act: -0.1700

Data Index: 5019780 (Open Web Text)

Max Activating Token Index: 757

Text #2

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.9113. Min Act: -0.1700

Data Index: 7639889 (Open Web Text)

Max Activating Token Index: 539

Text #3

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.9142. Min Act: -0.1700

Data Index: 7861525 (Open Web Text)

Max Activating Token Index: 929

Text #4

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.8934. Min Act: -0.1700

Data Index: 7555239 (Open Web Text)

Max Activating Token Index: 221

Text #5

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.8918. Min Act: -0.1700

Data Index: 1511406 (Open Web Text)

Max Activating Token Index: 398

Text #6

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.8937. Min Act: -0.1700

Data Index: 7023059 (Open Web Text)

Max Activating Token Index: 22

Text #7

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.8901. Min Act: -0.1700

Data Index: 7911592 (Open Web Text)

Max Activating Token Index: 719

Text #8

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.9101. Min Act: -0.1700

Data Index: 2730470 (Open Web Text)

Max Activating Token Index: 195

Text #9

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.8817. Min Act: -0.1700

Data Index: 7764634 (Open Web Text)

Max Activating Token Index: 742

Text #10

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.8785. Min Act: -0.1700

Data Index: 6742701 (Open Web Text)

Max Activating Token Index: 655

Text #11

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.8775. Min Act: -0.1700

Data Index: 3918671 (Open Web Text)

Max Activating Token Index: 14

Text #12

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.8679. Min Act: -0.1700

Data Index: 4465235 (Open Web Text)

Max Activating Token Index: 664

Text #13

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.8719. Min Act: -0.1700

Data Index: 455948 (Open Web Text)

Max Activating Token Index: 215

Text #14

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.8403. Min Act: -0.1700

Data Index: 3028442 (Open Web Text)

Max Activating Token Index: 1020

Text #15

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.8551. Min Act: -0.1700

Data Index: 3381632 (Open Web Text)

Max Activating Token Index: 202

Text #16

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.8553. Min Act: -0.1700

Data Index: 7715625 (Open Web Text)

Max Activating Token Index: 423

Text #17

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.8617. Min Act: -0.1700

Data Index: 1863122 (Open Web Text)

Max Activating Token Index: 485

Text #18

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.8352. Min Act: -0.1700

Data Index: 91110 (Open Web Text)

Max Activating Token Index: 83

Text #19

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.8209. Min Act: -0.1700

Data Index: 377227 (Open Web Text)

Max Activating Token Index: 321