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

Dataset: Open Web Text

Neuron 1463 in Layer 3

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: 4.7416. Min Range: -4.7416

Max Act: 4.7416. Min Act: -0.1700

Data Index: 3760822 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 4.7416. Min Range: -4.7416

Max Act: 4.7351. Min Act: -0.1700

Data Index: 7831970 (Open Web Text)

Max Activating Token Index: 127

Text #2

Max Range: 4.7416. Min Range: -4.7416

Max Act: 4.6963. Min Act: -0.1700

Data Index: 4785481 (Open Web Text)

Max Activating Token Index: 258

Text #3

Max Range: 4.7416. Min Range: -4.7416

Max Act: 4.6659. Min Act: -0.1700

Data Index: 4990037 (Open Web Text)

Max Activating Token Index: 245

Text #4

Max Range: 4.7416. Min Range: -4.7416

Max Act: 4.6712. Min Act: -0.1700

Data Index: 1005375 (Open Web Text)

Max Activating Token Index: 98

Text #5

Max Range: 4.7416. Min Range: -4.7416

Max Act: 4.6512. Min Act: -0.1700

Data Index: 8817407 (Open Web Text)

Max Activating Token Index: 679

Text #6

Max Range: 4.7416. Min Range: -4.7416

Max Act: 4.6331. Min Act: -0.1700

Data Index: 5087126 (Open Web Text)

Max Activating Token Index: 176

Text #7

Max Range: 4.7416. Min Range: -4.7416

Max Act: 4.6002. Min Act: -0.1700

Data Index: 8589341 (Open Web Text)

Max Activating Token Index: 199

Text #8

Max Range: 4.7416. Min Range: -4.7416

Max Act: 4.6438. Min Act: -0.1700

Data Index: 1753727 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 4.7416. Min Range: -4.7416

Max Act: 4.5910. Min Act: -0.1700

Data Index: 3185319 (Open Web Text)

Max Activating Token Index: 247

Text #10

Max Range: 4.7416. Min Range: -4.7416

Max Act: 4.6320. Min Act: -0.1700

Data Index: 2573667 (Open Web Text)

Max Activating Token Index: 762

Text #11

Max Range: 4.7416. Min Range: -4.7416

Max Act: 4.6190. Min Act: -0.1700

Data Index: 6529406 (Open Web Text)

Max Activating Token Index: 739

Text #12

Max Range: 4.7416. Min Range: -4.7416

Max Act: 4.5736. Min Act: -0.1700

Data Index: 2914381 (Open Web Text)

Max Activating Token Index: 246

Text #13

Max Range: 4.7416. Min Range: -4.7416

Max Act: 4.5739. Min Act: -0.1700

Data Index: 319909 (Open Web Text)

Max Activating Token Index: 181

Text #14

Max Range: 4.7416. Min Range: -4.7416

Max Act: 4.5711. Min Act: -0.1700

Data Index: 5772058 (Open Web Text)

Max Activating Token Index: 974

Text #15

Max Range: 4.7416. Min Range: -4.7416

Max Act: 4.5555. Min Act: -0.1700

Data Index: 4595067 (Open Web Text)

Max Activating Token Index: 617

Text #16

Max Range: 4.7416. Min Range: -4.7416

Max Act: 4.5897. Min Act: -0.1700

Data Index: 1419000 (Open Web Text)

Max Activating Token Index: 775

Text #17

Max Range: 4.7416. Min Range: -4.7416

Max Act: 4.5878. Min Act: -0.1700

Data Index: 3428263 (Open Web Text)

Max Activating Token Index: 763

Text #18

Max Range: 4.7416. Min Range: -4.7416

Max Act: 4.5998. Min Act: -0.1700

Data Index: 2354885 (Open Web Text)

Max Activating Token Index: 287

Text #19

Max Range: 4.7416. Min Range: -4.7416

Max Act: 4.5933. Min Act: -0.1700

Data Index: 2273978 (Open Web Text)

Max Activating Token Index: 683