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

Dataset: Open Web Text

Neuron 2355 in Layer 4

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: 5.0313. Min Range: -5.0313

Max Act: 5.0313. Min Act: -0.1700

Data Index: 4856338 (Open Web Text)

Max Activating Token Index: 374

Text #1

Max Range: 5.0313. Min Range: -5.0313

Max Act: 4.7816. Min Act: -0.1700

Data Index: 7390340 (Open Web Text)

Max Activating Token Index: 799

Text #2

Max Range: 5.0313. Min Range: -5.0313

Max Act: 4.7152. Min Act: -0.1700

Data Index: 2920737 (Open Web Text)

Max Activating Token Index: 798

Text #3

Max Range: 5.0313. Min Range: -5.0313

Max Act: 4.7054. Min Act: -0.1700

Data Index: 5220124 (Open Web Text)

Max Activating Token Index: 109

Text #4

Max Range: 5.0313. Min Range: -5.0313

Max Act: 4.6570. Min Act: -0.1700

Data Index: 2762062 (Open Web Text)

Max Activating Token Index: 299

Text #5

Max Range: 5.0313. Min Range: -5.0313

Max Act: 4.6855. Min Act: -0.1700

Data Index: 2729887 (Open Web Text)

Max Activating Token Index: 318

Text #6

Max Range: 5.0313. Min Range: -5.0313

Max Act: 4.6765. Min Act: -0.1700

Data Index: 3434648 (Open Web Text)

Max Activating Token Index: 522

Text #7

Max Range: 5.0313. Min Range: -5.0313

Max Act: 4.5436. Min Act: -0.1700

Data Index: 3776050 (Open Web Text)

Max Activating Token Index: 556

Text #8

Max Range: 5.0313. Min Range: -5.0313

Max Act: 4.5870. Min Act: -0.1700

Data Index: 1089305 (Open Web Text)

Max Activating Token Index: 74

Text #9

Max Range: 5.0313. Min Range: -5.0313

Max Act: 4.5927. Min Act: -0.1700

Data Index: 8658004 (Open Web Text)

Max Activating Token Index: 451

Text #10

Max Range: 5.0313. Min Range: -5.0313

Max Act: 4.5878. Min Act: -0.1700

Data Index: 5155480 (Open Web Text)

Max Activating Token Index: 40

Text #11

Max Range: 5.0313. Min Range: -5.0313

Max Act: 4.5998. Min Act: -0.1700

Data Index: 1474255 (Open Web Text)

Max Activating Token Index: 990

Text #12

Max Range: 5.0313. Min Range: -5.0313

Max Act: 4.6011. Min Act: -0.1700

Data Index: 3028621 (Open Web Text)

Max Activating Token Index: 633

Text #13

Max Range: 5.0313. Min Range: -5.0313

Max Act: 4.5824. Min Act: -0.1700

Data Index: 7148559 (Open Web Text)

Max Activating Token Index: 259

Text #14

Max Range: 5.0313. Min Range: -5.0313

Max Act: 4.5612. Min Act: -0.1700

Data Index: 2783196 (Open Web Text)

Max Activating Token Index: 441

Text #15

Max Range: 5.0313. Min Range: -5.0313

Max Act: 4.5377. Min Act: -0.1700

Data Index: 5486419 (Open Web Text)

Max Activating Token Index: 275

Text #16

Max Range: 5.0313. Min Range: -5.0313

Max Act: 4.5634. Min Act: -0.1700

Data Index: 4707761 (Open Web Text)

Max Activating Token Index: 887

Text #17

Max Range: 5.0313. Min Range: -5.0313

Max Act: 4.5684. Min Act: -0.1700

Data Index: 5717461 (Open Web Text)

Max Activating Token Index: 407

Text #18

Max Range: 5.0313. Min Range: -5.0313

Max Act: 4.4167. Min Act: -0.1700

Data Index: 559319 (Open Web Text)

Max Activating Token Index: 518

Text #19

Max Range: 5.0313. Min Range: -5.0313

Max Act: 4.5100. Min Act: -0.1700

Data Index: 5535699 (Open Web Text)

Max Activating Token Index: 926