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

Dataset: Open Web Text

Neuron 976 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: 3.5521. Min Range: -3.5521

Max Act: 3.5521. Min Act: -0.1700

Data Index: 5038693 (Open Web Text)

Max Activating Token Index: 362

Text #1

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.5117. Min Act: -0.1700

Data Index: 4909411 (Open Web Text)

Max Activating Token Index: 774

Text #2

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.5281. Min Act: -0.1700

Data Index: 965492 (Open Web Text)

Max Activating Token Index: 832

Text #3

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.4967. Min Act: -0.1700

Data Index: 7751325 (Open Web Text)

Max Activating Token Index: 903

Text #4

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.4650. Min Act: -0.1700

Data Index: 5664625 (Open Web Text)

Max Activating Token Index: 463

Text #5

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.3953. Min Act: -0.1700

Data Index: 2056895 (Open Web Text)

Max Activating Token Index: 878

Text #6

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.3770. Min Act: -0.1700

Data Index: 6091002 (Open Web Text)

Max Activating Token Index: 746

Text #7

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.3550. Min Act: -0.1700

Data Index: 5145315 (Open Web Text)

Max Activating Token Index: 502

Text #8

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.3716. Min Act: -0.1700

Data Index: 5852502 (Open Web Text)

Max Activating Token Index: 533

Text #9

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.3689. Min Act: -0.1700

Data Index: 1460352 (Open Web Text)

Max Activating Token Index: 433

Text #10

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.3242. Min Act: -0.1700

Data Index: 3699014 (Open Web Text)

Max Activating Token Index: 493

Text #11

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.3173. Min Act: -0.1700

Data Index: 1159081 (Open Web Text)

Max Activating Token Index: 774

Text #12

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.3489. Min Act: -0.1700

Data Index: 6059744 (Open Web Text)

Max Activating Token Index: 579

Text #13

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.3450. Min Act: -0.1700

Data Index: 7111673 (Open Web Text)

Max Activating Token Index: 627

Text #14

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.3277. Min Act: -0.1700

Data Index: 4054069 (Open Web Text)

Max Activating Token Index: 334

Text #15

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.3325. Min Act: -0.1700

Data Index: 2029227 (Open Web Text)

Max Activating Token Index: 501

Text #16

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.3318. Min Act: -0.1700

Data Index: 6315812 (Open Web Text)

Max Activating Token Index: 766

Text #17

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.3230. Min Act: -0.1700

Data Index: 4054846 (Open Web Text)

Max Activating Token Index: 232

Text #18

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.3204. Min Act: -0.1700

Data Index: 7223984 (Open Web Text)

Max Activating Token Index: 589

Text #19

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.3209. Min Act: -0.1700

Data Index: 1171532 (Open Web Text)

Max Activating Token Index: 699