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

Dataset: Open Web Text

Neuron 221 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: 3.6292. Min Range: -3.6292

Max Act: 3.6292. Min Act: -0.1700

Data Index: 5728184 (Open Web Text)

Max Activating Token Index: 430

Text #1

Max Range: 3.6292. Min Range: -3.6292

Max Act: 3.5545. Min Act: -0.1700

Data Index: 3461843 (Open Web Text)

Max Activating Token Index: 553

Text #2

Max Range: 3.6292. Min Range: -3.6292

Max Act: 3.4778. Min Act: -0.1700

Data Index: 472949 (Open Web Text)

Max Activating Token Index: 933

Text #3

Max Range: 3.6292. Min Range: -3.6292

Max Act: 3.4907. Min Act: -0.1700

Data Index: 4119367 (Open Web Text)

Max Activating Token Index: 880

Text #4

Max Range: 3.6292. Min Range: -3.6292

Max Act: 3.4262. Min Act: -0.1700

Data Index: 8175584 (Open Web Text)

Max Activating Token Index: 713

Text #5

Max Range: 3.6292. Min Range: -3.6292

Max Act: 3.4022. Min Act: -0.1700

Data Index: 3957866 (Open Web Text)

Max Activating Token Index: 139

Text #6

Max Range: 3.6292. Min Range: -3.6292

Max Act: 3.4045. Min Act: -0.1700

Data Index: 7815164 (Open Web Text)

Max Activating Token Index: 845

Text #7

Max Range: 3.6292. Min Range: -3.6292

Max Act: 3.3969. Min Act: -0.1700

Data Index: 4136933 (Open Web Text)

Max Activating Token Index: 389

Text #8

Max Range: 3.6292. Min Range: -3.6292

Max Act: 3.4010. Min Act: -0.1700

Data Index: 5695020 (Open Web Text)

Max Activating Token Index: 228

Text #9

Max Range: 3.6292. Min Range: -3.6292

Max Act: 3.3823. Min Act: -0.1700

Data Index: 7383787 (Open Web Text)

Max Activating Token Index: 927

Text #10

Max Range: 3.6292. Min Range: -3.6292

Max Act: 3.3603. Min Act: -0.1700

Data Index: 8826657 (Open Web Text)

Max Activating Token Index: 918

Text #11

Max Range: 3.6292. Min Range: -3.6292

Max Act: 3.3664. Min Act: -0.1700

Data Index: 6994062 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 3.6292. Min Range: -3.6292

Max Act: 3.3645. Min Act: -0.1700

Data Index: 2440450 (Open Web Text)

Max Activating Token Index: 561

Text #13

Max Range: 3.6292. Min Range: -3.6292

Max Act: 3.3760. Min Act: -0.1700

Data Index: 1933566 (Open Web Text)

Max Activating Token Index: 319

Text #14

Max Range: 3.6292. Min Range: -3.6292

Max Act: 3.3656. Min Act: -0.1700

Data Index: 5633690 (Open Web Text)

Max Activating Token Index: 984

Text #15

Max Range: 3.6292. Min Range: -3.6292

Max Act: 3.3662. Min Act: -0.1700

Data Index: 582227 (Open Web Text)

Max Activating Token Index: 434

Text #16

Max Range: 3.6292. Min Range: -3.6292

Max Act: 3.3416. Min Act: -0.1700

Data Index: 7541713 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 3.6292. Min Range: -3.6292

Max Act: 3.3386. Min Act: -0.1700

Data Index: 719965 (Open Web Text)

Max Activating Token Index: 978

Text #18

Max Range: 3.6292. Min Range: -3.6292

Max Act: 3.3304. Min Act: -0.1700

Data Index: 7534090 (Open Web Text)

Max Activating Token Index: 760

Text #19

Max Range: 3.6292. Min Range: -3.6292

Max Act: 3.3353. Min Act: -0.1700

Data Index: 4711989 (Open Web Text)

Max Activating Token Index: 886