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

Dataset: Open Web Text

Neuron 2928 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: 5.7416. Min Range: -5.7416

Max Act: 5.7416. Min Act: -0.1700

Data Index: 367342 (Open Web Text)

Max Activating Token Index: 573

Text #1

Max Range: 5.7416. Min Range: -5.7416

Max Act: 5.6988. Min Act: -0.1700

Data Index: 7811524 (Open Web Text)

Max Activating Token Index: 601

Text #2

Max Range: 5.7416. Min Range: -5.7416

Max Act: 5.7081. Min Act: -0.1700

Data Index: 8597040 (Open Web Text)

Max Activating Token Index: 211

Text #3

Max Range: 5.7416. Min Range: -5.7416

Max Act: 5.7053. Min Act: -0.1700

Data Index: 3278642 (Open Web Text)

Max Activating Token Index: 455

Text #4

Max Range: 5.7416. Min Range: -5.7416

Max Act: 5.6704. Min Act: -0.1700

Data Index: 1300559 (Open Web Text)

Max Activating Token Index: 226

Text #5

Max Range: 5.7416. Min Range: -5.7416

Max Act: 5.6422. Min Act: -0.1700

Data Index: 225022 (Open Web Text)

Max Activating Token Index: 611

Text #6

Max Range: 5.7416. Min Range: -5.7416

Max Act: 5.6356. Min Act: -0.1700

Data Index: 6829481 (Open Web Text)

Max Activating Token Index: 212

Text #7

Max Range: 5.7416. Min Range: -5.7416

Max Act: 5.6480. Min Act: -0.1700

Data Index: 4930109 (Open Web Text)

Max Activating Token Index: 373

Text #8

Max Range: 5.7416. Min Range: -5.7416

Max Act: 5.6404. Min Act: -0.1700

Data Index: 5978541 (Open Web Text)

Max Activating Token Index: 521

Text #9

Max Range: 5.7416. Min Range: -5.7416

Max Act: 5.5914. Min Act: -0.1700

Data Index: 1131049 (Open Web Text)

Max Activating Token Index: 365

Text #10

Max Range: 5.7416. Min Range: -5.7416

Max Act: 5.6005. Min Act: -0.1700

Data Index: 7216928 (Open Web Text)

Max Activating Token Index: 495

Text #11

Max Range: 5.7416. Min Range: -5.7416

Max Act: 5.6081. Min Act: -0.1700

Data Index: 3718906 (Open Web Text)

Max Activating Token Index: 478

Text #12

Max Range: 5.7416. Min Range: -5.7416

Max Act: 5.6028. Min Act: -0.1700

Data Index: 6498424 (Open Web Text)

Max Activating Token Index: 348

Text #13

Max Range: 5.7416. Min Range: -5.7416

Max Act: 5.6116. Min Act: -0.1700

Data Index: 6411209 (Open Web Text)

Max Activating Token Index: 150

Text #14

Max Range: 5.7416. Min Range: -5.7416

Max Act: 5.6095. Min Act: -0.1700

Data Index: 4255999 (Open Web Text)

Max Activating Token Index: 315

Text #15

Max Range: 5.7416. Min Range: -5.7416

Max Act: 5.6087. Min Act: -0.1700

Data Index: 4151720 (Open Web Text)

Max Activating Token Index: 990

Text #16

Max Range: 5.7416. Min Range: -5.7416

Max Act: 5.5815. Min Act: -0.1700

Data Index: 3972236 (Open Web Text)

Max Activating Token Index: 477

Text #17

Max Range: 5.7416. Min Range: -5.7416

Max Act: 5.5971. Min Act: -0.1700

Data Index: 2808268 (Open Web Text)

Max Activating Token Index: 417

Text #18

Max Range: 5.7416. Min Range: -5.7416

Max Act: 5.6080. Min Act: -0.1700

Data Index: 3969401 (Open Web Text)

Max Activating Token Index: 384

Text #19

Max Range: 5.7416. Min Range: -5.7416

Max Act: 5.6024. Min Act: -0.1700

Data Index: 1534613 (Open Web Text)

Max Activating Token Index: 335