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

Dataset: Open Web Text

Neuron 1402 in Layer 2

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: 1.8462. Min Range: -1.8462

Max Act: 1.8462. Min Act: -0.1700

Data Index: 5857739 (Open Web Text)

Max Activating Token Index: 578

Text #1

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.8450. Min Act: -0.1696

Data Index: 8699736 (Open Web Text)

Max Activating Token Index: 360

Text #2

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7733. Min Act: -0.1700

Data Index: 5874819 (Open Web Text)

Max Activating Token Index: 400

Text #3

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7476. Min Act: -0.1700

Data Index: 2195042 (Open Web Text)

Max Activating Token Index: 847

Text #4

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7338. Min Act: -0.1699

Data Index: 842793 (Open Web Text)

Max Activating Token Index: 473

Text #5

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7281. Min Act: -0.1700

Data Index: 2987446 (Open Web Text)

Max Activating Token Index: 802

Text #6

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7337. Min Act: -0.1695

Data Index: 2482 (Open Web Text)

Max Activating Token Index: 242

Text #7

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7204. Min Act: -0.1700

Data Index: 8371573 (Open Web Text)

Max Activating Token Index: 214

Text #8

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7174. Min Act: -0.1699

Data Index: 4514250 (Open Web Text)

Max Activating Token Index: 775

Text #9

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7075. Min Act: -0.1700

Data Index: 5575935 (Open Web Text)

Max Activating Token Index: 206

Text #10

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7073. Min Act: -0.1699

Data Index: 2575356 (Open Web Text)

Max Activating Token Index: 160

Text #11

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.6927. Min Act: -0.1700

Data Index: 2946356 (Open Web Text)

Max Activating Token Index: 113

Text #12

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.6839. Min Act: -0.1700

Data Index: 6464944 (Open Web Text)

Max Activating Token Index: 98

Text #13

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.6815. Min Act: -0.1698

Data Index: 5838760 (Open Web Text)

Max Activating Token Index: 309

Text #14

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.6845. Min Act: -0.1700

Data Index: 8211463 (Open Web Text)

Max Activating Token Index: 83

Text #15

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.6905. Min Act: -0.1700

Data Index: 6061841 (Open Web Text)

Max Activating Token Index: 526

Text #16

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.6609. Min Act: -0.1700

Data Index: 1779674 (Open Web Text)

Max Activating Token Index: 888

Text #17

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.6782. Min Act: -0.1689

Data Index: 1144281 (Open Web Text)

Max Activating Token Index: 447

Text #18

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.6630. Min Act: -0.1700

Data Index: 4335792 (Open Web Text)

Max Activating Token Index: 358

Text #19

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.6576. Min Act: -0.1683

Data Index: 4418491 (Open Web Text)

Max Activating Token Index: 608