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

Dataset: Open Web Text

Neuron 2769 in Layer 3

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: 3.9244. Min Range: -3.9244

Max Act: 3.9244. Min Act: -0.1700

Data Index: 1891094 (Open Web Text)

Max Activating Token Index: 468

Text #1

Max Range: 3.9244. Min Range: -3.9244

Max Act: 3.8430. Min Act: -0.1700

Data Index: 6037764 (Open Web Text)

Max Activating Token Index: 925

Text #2

Max Range: 3.9244. Min Range: -3.9244

Max Act: 3.8836. Min Act: -0.1700

Data Index: 4494161 (Open Web Text)

Max Activating Token Index: 951

Text #3

Max Range: 3.9244. Min Range: -3.9244

Max Act: 3.8571. Min Act: -0.1700

Data Index: 7586938 (Open Web Text)

Max Activating Token Index: 410

Text #4

Max Range: 3.9244. Min Range: -3.9244

Max Act: 3.8475. Min Act: -0.1700

Data Index: 2109020 (Open Web Text)

Max Activating Token Index: 579

Text #5

Max Range: 3.9244. Min Range: -3.9244

Max Act: 3.8123. Min Act: -0.1700

Data Index: 1876092 (Open Web Text)

Max Activating Token Index: 983

Text #6

Max Range: 3.9244. Min Range: -3.9244

Max Act: 3.8317. Min Act: -0.1700

Data Index: 2621595 (Open Web Text)

Max Activating Token Index: 802

Text #7

Max Range: 3.9244. Min Range: -3.9244

Max Act: 3.8356. Min Act: -0.1700

Data Index: 6120062 (Open Web Text)

Max Activating Token Index: 433

Text #8

Max Range: 3.9244. Min Range: -3.9244

Max Act: 3.8067. Min Act: -0.1700

Data Index: 8121147 (Open Web Text)

Max Activating Token Index: 76

Text #9

Max Range: 3.9244. Min Range: -3.9244

Max Act: 3.8333. Min Act: -0.1700

Data Index: 5849530 (Open Web Text)

Max Activating Token Index: 724

Text #10

Max Range: 3.9244. Min Range: -3.9244

Max Act: 3.8002. Min Act: -0.1700

Data Index: 5735150 (Open Web Text)

Max Activating Token Index: 817

Text #11

Max Range: 3.9244. Min Range: -3.9244

Max Act: 3.7909. Min Act: -0.1700

Data Index: 7934294 (Open Web Text)

Max Activating Token Index: 35

Text #12

Max Range: 3.9244. Min Range: -3.9244

Max Act: 3.7734. Min Act: -0.1700

Data Index: 7547645 (Open Web Text)

Max Activating Token Index: 167

Text #13

Max Range: 3.9244. Min Range: -3.9244

Max Act: 3.7879. Min Act: -0.1700

Data Index: 8478568 (Open Web Text)

Max Activating Token Index: 373

Text #14

Max Range: 3.9244. Min Range: -3.9244

Max Act: 3.8090. Min Act: -0.1700

Data Index: 1062772 (Open Web Text)

Max Activating Token Index: 491

Text #15

Max Range: 3.9244. Min Range: -3.9244

Max Act: 3.7821. Min Act: -0.1700

Data Index: 2892840 (Open Web Text)

Max Activating Token Index: 673

Text #16

Max Range: 3.9244. Min Range: -3.9244

Max Act: 3.8037. Min Act: -0.1700

Data Index: 635772 (Open Web Text)

Max Activating Token Index: 759

Text #17

Max Range: 3.9244. Min Range: -3.9244

Max Act: 3.7619. Min Act: -0.1700

Data Index: 2001936 (Open Web Text)

Max Activating Token Index: 969

Text #18

Max Range: 3.9244. Min Range: -3.9244

Max Act: 3.7861. Min Act: -0.1700

Data Index: 2002593 (Open Web Text)

Max Activating Token Index: 460

Text #19

Max Range: 3.9244. Min Range: -3.9244

Max Act: 3.7283. Min Act: -0.1700

Data Index: 6542404 (Open Web Text)

Max Activating Token Index: 614