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

Dataset: Open Web Text

Neuron 2033 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: 4.5809. Min Range: -4.5809

Max Act: 4.5809. Min Act: -0.1700

Data Index: 8731465 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.5399. Min Act: -0.1700

Data Index: 8751345 (Open Web Text)

Max Activating Token Index: 711

Text #2

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.5509. Min Act: -0.1700

Data Index: 2958488 (Open Web Text)

Max Activating Token Index: 593

Text #3

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.5329. Min Act: -0.1700

Data Index: 1265622 (Open Web Text)

Max Activating Token Index: 529

Text #4

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.4534. Min Act: -0.1700

Data Index: 4938924 (Open Web Text)

Max Activating Token Index: 78

Text #5

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.4626. Min Act: -0.1700

Data Index: 4866058 (Open Web Text)

Max Activating Token Index: 718

Text #6

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.4385. Min Act: -0.1700

Data Index: 321679 (Open Web Text)

Max Activating Token Index: 165

Text #7

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.3983. Min Act: -0.1700

Data Index: 8006993 (Open Web Text)

Max Activating Token Index: 305

Text #8

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.4419. Min Act: -0.1700

Data Index: 1674750 (Open Web Text)

Max Activating Token Index: 652

Text #9

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.4547. Min Act: -0.1700

Data Index: 3062566 (Open Web Text)

Max Activating Token Index: 682

Text #10

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.4149. Min Act: -0.1700

Data Index: 8529387 (Open Web Text)

Max Activating Token Index: 763

Text #11

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.3761. Min Act: -0.1700

Data Index: 6263463 (Open Web Text)

Max Activating Token Index: 901

Text #12

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.3794. Min Act: -0.1700

Data Index: 5412270 (Open Web Text)

Max Activating Token Index: 918

Text #13

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.3708. Min Act: -0.1700

Data Index: 5736175 (Open Web Text)

Max Activating Token Index: 633

Text #14

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.3799. Min Act: -0.1700

Data Index: 6973003 (Open Web Text)

Max Activating Token Index: 494

Text #15

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.3674. Min Act: -0.1700

Data Index: 6731821 (Open Web Text)

Max Activating Token Index: 39

Text #16

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.3482. Min Act: -0.1700

Data Index: 2088517 (Open Web Text)

Max Activating Token Index: 155

Text #17

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.3128. Min Act: -0.1700

Data Index: 205992 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.3082. Min Act: -0.1700

Data Index: 6782470 (Open Web Text)

Max Activating Token Index: 696

Text #19

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.3292. Min Act: -0.1700

Data Index: 5957048 (Open Web Text)

Max Activating Token Index: 1004