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

Dataset: Open Web Text

Neuron 361 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: 4.2800. Min Range: -4.2800

Max Act: 4.2800. Min Act: -0.1700

Data Index: 102596 (Open Web Text)

Max Activating Token Index: 929

Text #1

Max Range: 4.2800. Min Range: -4.2800

Max Act: 3.9662. Min Act: -0.1700

Data Index: 2349056 (Open Web Text)

Max Activating Token Index: 940

Text #2

Max Range: 4.2800. Min Range: -4.2800

Max Act: 3.9346. Min Act: -0.1700

Data Index: 6339034 (Open Web Text)

Max Activating Token Index: 557

Text #3

Max Range: 4.2800. Min Range: -4.2800

Max Act: 3.9294. Min Act: -0.1700

Data Index: 2917762 (Open Web Text)

Max Activating Token Index: 179

Text #4

Max Range: 4.2800. Min Range: -4.2800

Max Act: 3.8560. Min Act: -0.1700

Data Index: 2047085 (Open Web Text)

Max Activating Token Index: 396

Text #5

Max Range: 4.2800. Min Range: -4.2800

Max Act: 3.7839. Min Act: -0.1700

Data Index: 4323660 (Open Web Text)

Max Activating Token Index: 144

Text #6

Max Range: 4.2800. Min Range: -4.2800

Max Act: 3.7523. Min Act: -0.1700

Data Index: 6060496 (Open Web Text)

Max Activating Token Index: 1021

Text #7

Max Range: 4.2800. Min Range: -4.2800

Max Act: 3.7449. Min Act: -0.1700

Data Index: 6578710 (Open Web Text)

Max Activating Token Index: 451

Text #8

Max Range: 4.2800. Min Range: -4.2800

Max Act: 3.7854. Min Act: -0.1700

Data Index: 1683690 (Open Web Text)

Max Activating Token Index: 556

Text #9

Max Range: 4.2800. Min Range: -4.2800

Max Act: 3.7351. Min Act: -0.1700

Data Index: 6744350 (Open Web Text)

Max Activating Token Index: 203

Text #10

Max Range: 4.2800. Min Range: -4.2800

Max Act: 3.7706. Min Act: -0.1700

Data Index: 2197968 (Open Web Text)

Max Activating Token Index: 221

Text #11

Max Range: 4.2800. Min Range: -4.2800

Max Act: 3.7430. Min Act: -0.1700

Data Index: 5382647 (Open Web Text)

Max Activating Token Index: 1015

Text #12

Max Range: 4.2800. Min Range: -4.2800

Max Act: 3.7178. Min Act: -0.1700

Data Index: 6886550 (Open Web Text)

Max Activating Token Index: 427

Text #13

Max Range: 4.2800. Min Range: -4.2800

Max Act: 3.7446. Min Act: -0.1700

Data Index: 7387658 (Open Web Text)

Max Activating Token Index: 768

Text #14

Max Range: 4.2800. Min Range: -4.2800

Max Act: 3.7341. Min Act: -0.1700

Data Index: 4763180 (Open Web Text)

Max Activating Token Index: 292

Text #15

Max Range: 4.2800. Min Range: -4.2800

Max Act: 3.7642. Min Act: -0.1700

Data Index: 6879349 (Open Web Text)

Max Activating Token Index: 452

Text #16

Max Range: 4.2800. Min Range: -4.2800

Max Act: 3.7318. Min Act: -0.1700

Data Index: 5248953 (Open Web Text)

Max Activating Token Index: 782

Text #17

Max Range: 4.2800. Min Range: -4.2800

Max Act: 3.7042. Min Act: -0.1700

Data Index: 1579426 (Open Web Text)

Max Activating Token Index: 822

Text #18

Max Range: 4.2800. Min Range: -4.2800

Max Act: 3.6393. Min Act: -0.1700

Data Index: 5601332 (Open Web Text)

Max Activating Token Index: 1002

Text #19

Max Range: 4.2800. Min Range: -4.2800

Max Act: 3.6788. Min Act: -0.1700

Data Index: 2524059 (Open Web Text)

Max Activating Token Index: 890