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

Dataset: Open Web Text

Neuron 2728 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: 2.0957. Min Range: -2.0957

Max Act: 2.0957. Min Act: -0.1700

Data Index: 7848661 (Open Web Text)

Max Activating Token Index: 572

Text #1

Max Range: 2.0957. Min Range: -2.0957

Max Act: 2.0885. Min Act: -0.1700

Data Index: 3367352 (Open Web Text)

Max Activating Token Index: 574

Text #2

Max Range: 2.0957. Min Range: -2.0957

Max Act: 2.0622. Min Act: -0.1700

Data Index: 6224616 (Open Web Text)

Max Activating Token Index: 172

Text #3

Max Range: 2.0957. Min Range: -2.0957

Max Act: 2.0624. Min Act: -0.1700

Data Index: 306657 (Open Web Text)

Max Activating Token Index: 214

Text #4

Max Range: 2.0957. Min Range: -2.0957

Max Act: 2.0481. Min Act: -0.1700

Data Index: 1787800 (Open Web Text)

Max Activating Token Index: 563

Text #5

Max Range: 2.0957. Min Range: -2.0957

Max Act: 2.0492. Min Act: -0.1700

Data Index: 7553807 (Open Web Text)

Max Activating Token Index: 743

Text #6

Max Range: 2.0957. Min Range: -2.0957

Max Act: 2.0286. Min Act: -0.1700

Data Index: 402690 (Open Web Text)

Max Activating Token Index: 489

Text #7

Max Range: 2.0957. Min Range: -2.0957

Max Act: 2.0358. Min Act: -0.1700

Data Index: 4931561 (Open Web Text)

Max Activating Token Index: 723

Text #8

Max Range: 2.0957. Min Range: -2.0957

Max Act: 2.0250. Min Act: -0.1700

Data Index: 8588810 (Open Web Text)

Max Activating Token Index: 506

Text #9

Max Range: 2.0957. Min Range: -2.0957

Max Act: 2.0308. Min Act: -0.1700

Data Index: 8771759 (Open Web Text)

Max Activating Token Index: 586

Text #10

Max Range: 2.0957. Min Range: -2.0957

Max Act: 2.0288. Min Act: -0.1700

Data Index: 2935005 (Open Web Text)

Max Activating Token Index: 171

Text #11

Max Range: 2.0957. Min Range: -2.0957

Max Act: 2.0351. Min Act: -0.1700

Data Index: 1094398 (Open Web Text)

Max Activating Token Index: 614

Text #12

Max Range: 2.0957. Min Range: -2.0957

Max Act: 2.0318. Min Act: -0.1700

Data Index: 3450656 (Open Web Text)

Max Activating Token Index: 741

Text #13

Max Range: 2.0957. Min Range: -2.0957

Max Act: 2.0201. Min Act: -0.1700

Data Index: 6932665 (Open Web Text)

Max Activating Token Index: 825

Text #14

Max Range: 2.0957. Min Range: -2.0957

Max Act: 2.0104. Min Act: -0.1700

Data Index: 8689202 (Open Web Text)

Max Activating Token Index: 951

Text #15

Max Range: 2.0957. Min Range: -2.0957

Max Act: 2.0284. Min Act: -0.1700

Data Index: 110754 (Open Web Text)

Max Activating Token Index: 514

Text #16

Max Range: 2.0957. Min Range: -2.0957

Max Act: 2.0245. Min Act: -0.1700

Data Index: 3726975 (Open Web Text)

Max Activating Token Index: 548

Text #17

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.9908. Min Act: -0.1700

Data Index: 6561464 (Open Web Text)

Max Activating Token Index: 727

Text #18

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.9951. Min Act: -0.1700

Data Index: 5479531 (Open Web Text)

Max Activating Token Index: 401

Text #19

Max Range: 2.0957. Min Range: -2.0957

Max Act: 2.0024. Min Act: -0.1700

Data Index: 2539305 (Open Web Text)

Max Activating Token Index: 311