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

Dataset: Open Web Text

Neuron 290 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: 1.4487. Min Range: -1.4487

Max Act: 1.4487. Min Act: -0.0948

Data Index: 5881090 (Open Web Text)

Max Activating Token Index: 951

Text #1

Max Range: 1.4487. Min Range: -1.4487

Max Act: 1.4073. Min Act: -0.1022

Data Index: 5647373 (Open Web Text)

Max Activating Token Index: 487

Text #2

Max Range: 1.4487. Min Range: -1.4487

Max Act: 1.4067. Min Act: -0.0948

Data Index: 6849033 (Open Web Text)

Max Activating Token Index: 132

Text #3

Max Range: 1.4487. Min Range: -1.4487

Max Act: 1.3888. Min Act: -0.0948

Data Index: 1840953 (Open Web Text)

Max Activating Token Index: 383

Text #4

Max Range: 1.4487. Min Range: -1.4487

Max Act: 1.3985. Min Act: -0.0948

Data Index: 1402189 (Open Web Text)

Max Activating Token Index: 379

Text #5

Max Range: 1.4487. Min Range: -1.4487

Max Act: 1.3883. Min Act: -0.0948

Data Index: 4468735 (Open Web Text)

Max Activating Token Index: 642

Text #6

Max Range: 1.4487. Min Range: -1.4487

Max Act: 1.3916. Min Act: -0.0948

Data Index: 4919695 (Open Web Text)

Max Activating Token Index: 871

Text #7

Max Range: 1.4487. Min Range: -1.4487

Max Act: 1.3838. Min Act: -0.1353

Data Index: 4374562 (Open Web Text)

Max Activating Token Index: 357

Text #8

Max Range: 1.4487. Min Range: -1.4487

Max Act: 1.3726. Min Act: -0.0948

Data Index: 7602687 (Open Web Text)

Max Activating Token Index: 334

Text #9

Max Range: 1.4487. Min Range: -1.4487

Max Act: 1.3795. Min Act: -0.0948

Data Index: 2167427 (Open Web Text)

Max Activating Token Index: 211

Text #10

Max Range: 1.4487. Min Range: -1.4487

Max Act: 1.3720. Min Act: -0.1357

Data Index: 6400699 (Open Web Text)

Max Activating Token Index: 879

Text #11

Max Range: 1.4487. Min Range: -1.4487

Max Act: 1.3777. Min Act: -0.0948

Data Index: 1126818 (Open Web Text)

Max Activating Token Index: 297

Text #12

Max Range: 1.4487. Min Range: -1.4487

Max Act: 1.3673. Min Act: -0.0948

Data Index: 1417294 (Open Web Text)

Max Activating Token Index: 404

Text #13

Max Range: 1.4487. Min Range: -1.4487

Max Act: 1.3663. Min Act: -0.1267

Data Index: 6934372 (Open Web Text)

Max Activating Token Index: 641

Text #14

Max Range: 1.4487. Min Range: -1.4487

Max Act: 1.3711. Min Act: -0.1510

Data Index: 4744180 (Open Web Text)

Max Activating Token Index: 386

Text #15

Max Range: 1.4487. Min Range: -1.4487

Max Act: 1.3668. Min Act: -0.0948

Data Index: 6085170 (Open Web Text)

Max Activating Token Index: 795

Text #16

Max Range: 1.4487. Min Range: -1.4487

Max Act: 1.3725. Min Act: -0.1128

Data Index: 2393015 (Open Web Text)

Max Activating Token Index: 944

Text #17

Max Range: 1.4487. Min Range: -1.4487

Max Act: 1.3651. Min Act: -0.0948

Data Index: 4314705 (Open Web Text)

Max Activating Token Index: 975

Text #18

Max Range: 1.4487. Min Range: -1.4487

Max Act: 1.3682. Min Act: -0.0948

Data Index: 3390085 (Open Web Text)

Max Activating Token Index: 839

Text #19

Max Range: 1.4487. Min Range: -1.4487

Max Act: 1.3637. Min Act: -0.0948

Data Index: 711610 (Open Web Text)

Max Activating Token Index: 435