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

Dataset: Open Web Text

Neuron 2354 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: 1.4195. Min Range: -1.4195

Max Act: 1.4195. Min Act: -0.1700

Data Index: 3905366 (Open Web Text)

Max Activating Token Index: 642

Text #1

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.4186. Min Act: -0.1700

Data Index: 4823444 (Open Web Text)

Max Activating Token Index: 432

Text #2

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.4036. Min Act: -0.1700

Data Index: 7609856 (Open Web Text)

Max Activating Token Index: 371

Text #3

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.3963. Min Act: -0.1698

Data Index: 5739035 (Open Web Text)

Max Activating Token Index: 289

Text #4

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.3958. Min Act: -0.1690

Data Index: 829090 (Open Web Text)

Max Activating Token Index: 533

Text #5

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.3766. Min Act: -0.1700

Data Index: 3058936 (Open Web Text)

Max Activating Token Index: 670

Text #6

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.3785. Min Act: -0.1688

Data Index: 54402 (Open Web Text)

Max Activating Token Index: 225

Text #7

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.3706. Min Act: -0.1700

Data Index: 2001848 (Open Web Text)

Max Activating Token Index: 17

Text #8

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.3715. Min Act: -0.1700

Data Index: 8666707 (Open Web Text)

Max Activating Token Index: 385

Text #9

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.3624. Min Act: -0.1699

Data Index: 376393 (Open Web Text)

Max Activating Token Index: 181

Text #10

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.3625. Min Act: -0.1700

Data Index: 3634705 (Open Web Text)

Max Activating Token Index: 94

Text #11

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.3637. Min Act: -0.1700

Data Index: 442700 (Open Web Text)

Max Activating Token Index: 184

Text #12

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.3648. Min Act: -0.1699

Data Index: 4217662 (Open Web Text)

Max Activating Token Index: 262

Text #13

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.3587. Min Act: -0.1700

Data Index: 4625104 (Open Web Text)

Max Activating Token Index: 402

Text #14

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.3541. Min Act: -0.1700

Data Index: 3558641 (Open Web Text)

Max Activating Token Index: 101

Text #15

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.3470. Min Act: -0.1700

Data Index: 1862634 (Open Web Text)

Max Activating Token Index: 370

Text #16

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.3446. Min Act: -0.1700

Data Index: 3745497 (Open Web Text)

Max Activating Token Index: 136

Text #17

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.3525. Min Act: -0.1700

Data Index: 4064476 (Open Web Text)

Max Activating Token Index: 277

Text #18

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.3509. Min Act: -0.1700

Data Index: 8347164 (Open Web Text)

Max Activating Token Index: 323

Text #19

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.3533. Min Act: -0.1698

Data Index: 2483935 (Open Web Text)

Max Activating Token Index: 598