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

Dataset: Open Web Text

Neuron 169 in Layer 0

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: 1.5707. Min Range: -1.5707

Max Act: 1.5707. Min Act: -0.0680

Data Index: 8173210 (Open Web Text)

Max Activating Token Index: 833

Text #1

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.5286. Min Act: -0.0781

Data Index: 2342238 (Open Web Text)

Max Activating Token Index: 879

Text #2

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.5301. Min Act: -0.1177

Data Index: 4117991 (Open Web Text)

Max Activating Token Index: 762

Text #3

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.5141. Min Act: -0.1362

Data Index: 8332141 (Open Web Text)

Max Activating Token Index: 619

Text #4

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.5081. Min Act: -0.0930

Data Index: 3478496 (Open Web Text)

Max Activating Token Index: 699

Text #5

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.5078. Min Act: -0.1239

Data Index: 7582549 (Open Web Text)

Max Activating Token Index: 722

Text #6

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.4847. Min Act: -0.0572

Data Index: 3810196 (Open Web Text)

Max Activating Token Index: 213

Text #7

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.4927. Min Act: -0.0521

Data Index: 3261010 (Open Web Text)

Max Activating Token Index: 814

Text #8

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.4914. Min Act: -0.0512

Data Index: 8371280 (Open Web Text)

Max Activating Token Index: 897

Text #9

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.4925. Min Act: -0.0952

Data Index: 4146520 (Open Web Text)

Max Activating Token Index: 710

Text #10

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.4758. Min Act: -0.0569

Data Index: 692441 (Open Web Text)

Max Activating Token Index: 799

Text #11

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.4780. Min Act: -0.0928

Data Index: 5681675 (Open Web Text)

Max Activating Token Index: 513

Text #12

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.4784. Min Act: -0.0850

Data Index: 6132720 (Open Web Text)

Max Activating Token Index: 485

Text #13

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.4736. Min Act: -0.0711

Data Index: 8295429 (Open Web Text)

Max Activating Token Index: 718

Text #14

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.4734. Min Act: -0.1182

Data Index: 5370786 (Open Web Text)

Max Activating Token Index: 776

Text #15

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.4704. Min Act: -0.1286

Data Index: 1493426 (Open Web Text)

Max Activating Token Index: 830

Text #16

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.4671. Min Act: -0.1040

Data Index: 1242937 (Open Web Text)

Max Activating Token Index: 368

Text #17

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.4660. Min Act: -0.0972

Data Index: 8187589 (Open Web Text)

Max Activating Token Index: 838

Text #18

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.4622. Min Act: -0.1320

Data Index: 7836932 (Open Web Text)

Max Activating Token Index: 400

Text #19

Max Range: 1.5707. Min Range: -1.5707

Max Act: 1.4619. Min Act: -0.0617

Data Index: 5756979 (Open Web Text)

Max Activating Token Index: 233