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

Dataset: Open Web Text

Neuron 1592 in Layer 1

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: 3.9692. Min Range: -3.9692

Max Act: 3.9692. Min Act: -0.1700

Data Index: 2183236 (Open Web Text)

Max Activating Token Index: 47

Text #1

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.5596. Min Act: -0.1700

Data Index: 4829621 (Open Web Text)

Max Activating Token Index: 505

Text #2

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.5499. Min Act: -0.1700

Data Index: 5220008 (Open Web Text)

Max Activating Token Index: 640

Text #3

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.5298. Min Act: -0.1700

Data Index: 8541190 (Open Web Text)

Max Activating Token Index: 465

Text #4

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.5206. Min Act: -0.1700

Data Index: 3954898 (Open Web Text)

Max Activating Token Index: 780

Text #5

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.4385. Min Act: -0.1700

Data Index: 6948125 (Open Web Text)

Max Activating Token Index: 336

Text #6

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.4396. Min Act: -0.1700

Data Index: 7278867 (Open Web Text)

Max Activating Token Index: 612

Text #7

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.4298. Min Act: -0.1700

Data Index: 6506964 (Open Web Text)

Max Activating Token Index: 629

Text #8

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.4453. Min Act: -0.1700

Data Index: 6335051 (Open Web Text)

Max Activating Token Index: 864

Text #9

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.4127. Min Act: -0.1700

Data Index: 4666231 (Open Web Text)

Max Activating Token Index: 294

Text #10

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.3826. Min Act: -0.1700

Data Index: 3858167 (Open Web Text)

Max Activating Token Index: 883

Text #11

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.3741. Min Act: -0.1700

Data Index: 5764351 (Open Web Text)

Max Activating Token Index: 287

Text #12

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.3796. Min Act: -0.1700

Data Index: 1154224 (Open Web Text)

Max Activating Token Index: 284

Text #13

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.3264. Min Act: -0.1700

Data Index: 10104 (Open Web Text)

Max Activating Token Index: 122

Text #14

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.3173. Min Act: -0.1700

Data Index: 5971652 (Open Web Text)

Max Activating Token Index: 517

Text #15

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.3422. Min Act: -0.1700

Data Index: 5905710 (Open Web Text)

Max Activating Token Index: 465

Text #16

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.3065. Min Act: -0.1700

Data Index: 1117481 (Open Web Text)

Max Activating Token Index: 44

Text #17

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.3176. Min Act: -0.1700

Data Index: 4775636 (Open Web Text)

Max Activating Token Index: 676

Text #18

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.2932. Min Act: -0.1700

Data Index: 7923862 (Open Web Text)

Max Activating Token Index: 521

Text #19

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.3007. Min Act: -0.1700

Data Index: 2617258 (Open Web Text)

Max Activating Token Index: 443