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

Dataset: Open Web Text

Neuron 851 in Layer 6

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: 3.4765. Min Range: -3.4765

Max Act: 3.4765. Min Act: -0.1700

Data Index: 3425678 (Open Web Text)

Max Activating Token Index: 860

Text #1

Max Range: 3.4765. Min Range: -3.4765

Max Act: 3.4269. Min Act: -0.1700

Data Index: 5761947 (Open Web Text)

Max Activating Token Index: 901

Text #2

Max Range: 3.4765. Min Range: -3.4765

Max Act: 3.4059. Min Act: -0.1700

Data Index: 6763335 (Open Web Text)

Max Activating Token Index: 388

Text #3

Max Range: 3.4765. Min Range: -3.4765

Max Act: 3.3944. Min Act: -0.1700

Data Index: 808511 (Open Web Text)

Max Activating Token Index: 586

Text #4

Max Range: 3.4765. Min Range: -3.4765

Max Act: 3.3951. Min Act: -0.1700

Data Index: 2725519 (Open Web Text)

Max Activating Token Index: 519

Text #5

Max Range: 3.4765. Min Range: -3.4765

Max Act: 3.3648. Min Act: -0.1700

Data Index: 7721484 (Open Web Text)

Max Activating Token Index: 360

Text #6

Max Range: 3.4765. Min Range: -3.4765

Max Act: 3.3872. Min Act: -0.1700

Data Index: 7966464 (Open Web Text)

Max Activating Token Index: 403

Text #7

Max Range: 3.4765. Min Range: -3.4765

Max Act: 3.3518. Min Act: -0.1700

Data Index: 794747 (Open Web Text)

Max Activating Token Index: 374

Text #8

Max Range: 3.4765. Min Range: -3.4765

Max Act: 3.3384. Min Act: -0.1700

Data Index: 8010710 (Open Web Text)

Max Activating Token Index: 236

Text #9

Max Range: 3.4765. Min Range: -3.4765

Max Act: 3.3433. Min Act: -0.1700

Data Index: 1408545 (Open Web Text)

Max Activating Token Index: 1016

Text #10

Max Range: 3.4765. Min Range: -3.4765

Max Act: 3.2990. Min Act: -0.1700

Data Index: 859172 (Open Web Text)

Max Activating Token Index: 577

Text #11

Max Range: 3.4765. Min Range: -3.4765

Max Act: 3.3156. Min Act: -0.1700

Data Index: 4348575 (Open Web Text)

Max Activating Token Index: 993

Text #12

Max Range: 3.4765. Min Range: -3.4765

Max Act: 3.3242. Min Act: -0.1700

Data Index: 3548976 (Open Web Text)

Max Activating Token Index: 427

Text #13

Max Range: 3.4765. Min Range: -3.4765

Max Act: 3.3375. Min Act: -0.1700

Data Index: 4686418 (Open Web Text)

Max Activating Token Index: 363

Text #14

Max Range: 3.4765. Min Range: -3.4765

Max Act: 3.3064. Min Act: -0.1700

Data Index: 2700276 (Open Web Text)

Max Activating Token Index: 454

Text #15

Max Range: 3.4765. Min Range: -3.4765

Max Act: 3.3115. Min Act: -0.1700

Data Index: 1339623 (Open Web Text)

Max Activating Token Index: 648

Text #16

Max Range: 3.4765. Min Range: -3.4765

Max Act: 3.2970. Min Act: -0.1700

Data Index: 4684075 (Open Web Text)

Max Activating Token Index: 422

Text #17

Max Range: 3.4765. Min Range: -3.4765

Max Act: 3.3141. Min Act: -0.1700

Data Index: 3131067 (Open Web Text)

Max Activating Token Index: 261

Text #18

Max Range: 3.4765. Min Range: -3.4765

Max Act: 3.3111. Min Act: -0.1700

Data Index: 4977123 (Open Web Text)

Max Activating Token Index: 438

Text #19

Max Range: 3.4765. Min Range: -3.4765

Max Act: 3.3104. Min Act: -0.1700

Data Index: 7657402 (Open Web Text)

Max Activating Token Index: 478