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

Dataset: Open Web Text

Neuron 2842 in Layer 5

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: 4.9984. Min Range: -4.9984

Max Act: 4.9984. Min Act: -0.1700

Data Index: 5876400 (Open Web Text)

Max Activating Token Index: 666

Text #1

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.8899. Min Act: -0.1700

Data Index: 6588767 (Open Web Text)

Max Activating Token Index: 380

Text #2

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.9125. Min Act: -0.1700

Data Index: 4256619 (Open Web Text)

Max Activating Token Index: 610

Text #3

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.9230. Min Act: -0.1700

Data Index: 3033682 (Open Web Text)

Max Activating Token Index: 370

Text #4

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.9010. Min Act: -0.1700

Data Index: 5025174 (Open Web Text)

Max Activating Token Index: 274

Text #5

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.8784. Min Act: -0.1700

Data Index: 6296522 (Open Web Text)

Max Activating Token Index: 377

Text #6

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.8608. Min Act: -0.1700

Data Index: 6713568 (Open Web Text)

Max Activating Token Index: 487

Text #7

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.7958. Min Act: -0.1700

Data Index: 3865451 (Open Web Text)

Max Activating Token Index: 291

Text #8

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.8013. Min Act: -0.1700

Data Index: 7429051 (Open Web Text)

Max Activating Token Index: 931

Text #9

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.8017. Min Act: -0.1700

Data Index: 1492702 (Open Web Text)

Max Activating Token Index: 390

Text #10

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.7704. Min Act: -0.1700

Data Index: 771198 (Open Web Text)

Max Activating Token Index: 582

Text #11

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.7646. Min Act: -0.1700

Data Index: 1391707 (Open Web Text)

Max Activating Token Index: 429

Text #12

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.7944. Min Act: -0.1700

Data Index: 1055649 (Open Web Text)

Max Activating Token Index: 355

Text #13

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.7799. Min Act: -0.1700

Data Index: 8569087 (Open Web Text)

Max Activating Token Index: 562

Text #14

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.7658. Min Act: -0.1700

Data Index: 3117869 (Open Web Text)

Max Activating Token Index: 993

Text #15

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.7457. Min Act: -0.1700

Data Index: 4109468 (Open Web Text)

Max Activating Token Index: 414

Text #16

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.7622. Min Act: -0.1700

Data Index: 5814599 (Open Web Text)

Max Activating Token Index: 364

Text #17

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.7612. Min Act: -0.1700

Data Index: 1476304 (Open Web Text)

Max Activating Token Index: 840

Text #18

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.8062. Min Act: -0.1700

Data Index: 1815921 (Open Web Text)

Max Activating Token Index: 913

Text #19

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.7399. Min Act: -0.1700

Data Index: 5972329 (Open Web Text)

Max Activating Token Index: 357