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

Dataset: Open Web Text

Neuron 1397 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: 4.4974. Min Range: -4.4974

Max Act: 4.4737. Min Act: -0.1700

Data Index: 1899789 (Open Web Text)

Max Activating Token Index: 164

Text #1

Max Range: 4.4974. Min Range: -4.4974

Max Act: 4.4613. Min Act: -0.1700

Data Index: 7844263 (Open Web Text)

Max Activating Token Index: 739

Text #2

Max Range: 4.4974. Min Range: -4.4974

Max Act: 4.4974. Min Act: -0.1700

Data Index: 5922929 (Open Web Text)

Max Activating Token Index: 838

Text #3

Max Range: 4.4974. Min Range: -4.4974

Max Act: 4.4550. Min Act: -0.1700

Data Index: 8479884 (Open Web Text)

Max Activating Token Index: 819

Text #4

Max Range: 4.4974. Min Range: -4.4974

Max Act: 4.4581. Min Act: -0.1700

Data Index: 1517654 (Open Web Text)

Max Activating Token Index: 344

Text #5

Max Range: 4.4974. Min Range: -4.4974

Max Act: 4.4280. Min Act: -0.1700

Data Index: 3701847 (Open Web Text)

Max Activating Token Index: 688

Text #6

Max Range: 4.4974. Min Range: -4.4974

Max Act: 4.4628. Min Act: -0.1700

Data Index: 2821077 (Open Web Text)

Max Activating Token Index: 687

Text #7

Max Range: 4.4974. Min Range: -4.4974

Max Act: 4.4265. Min Act: -0.1700

Data Index: 4352135 (Open Web Text)

Max Activating Token Index: 586

Text #8

Max Range: 4.4974. Min Range: -4.4974

Max Act: 4.3984. Min Act: -0.1700

Data Index: 4389502 (Open Web Text)

Max Activating Token Index: 495

Text #9

Max Range: 4.4974. Min Range: -4.4974

Max Act: 4.4249. Min Act: -0.1700

Data Index: 3773399 (Open Web Text)

Max Activating Token Index: 352

Text #10

Max Range: 4.4974. Min Range: -4.4974

Max Act: 4.3981. Min Act: -0.1700

Data Index: 6884942 (Open Web Text)

Max Activating Token Index: 347

Text #11

Max Range: 4.4974. Min Range: -4.4974

Max Act: 4.4204. Min Act: -0.1700

Data Index: 8771 (Open Web Text)

Max Activating Token Index: 864

Text #12

Max Range: 4.4974. Min Range: -4.4974

Max Act: 4.4137. Min Act: -0.1700

Data Index: 4178720 (Open Web Text)

Max Activating Token Index: 943

Text #13

Max Range: 4.4974. Min Range: -4.4974

Max Act: 4.3903. Min Act: -0.1700

Data Index: 5033756 (Open Web Text)

Max Activating Token Index: 471

Text #14

Max Range: 4.4974. Min Range: -4.4974

Max Act: 4.3681. Min Act: -0.1700

Data Index: 4268204 (Open Web Text)

Max Activating Token Index: 466

Text #15

Max Range: 4.4974. Min Range: -4.4974

Max Act: 4.3868. Min Act: -0.1700

Data Index: 5987007 (Open Web Text)

Max Activating Token Index: 596

Text #16

Max Range: 4.4974. Min Range: -4.4974

Max Act: 4.3715. Min Act: -0.1700

Data Index: 6409513 (Open Web Text)

Max Activating Token Index: 336

Text #17

Max Range: 4.4974. Min Range: -4.4974

Max Act: 4.3870. Min Act: -0.1700

Data Index: 6952013 (Open Web Text)

Max Activating Token Index: 379

Text #18

Max Range: 4.4974. Min Range: -4.4974

Max Act: 4.3745. Min Act: -0.1700

Data Index: 1448874 (Open Web Text)

Max Activating Token Index: 120

Text #19

Max Range: 4.4974. Min Range: -4.4974

Max Act: 4.3893. Min Act: -0.1700

Data Index: 222232 (Open Web Text)

Max Activating Token Index: 746