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

Dataset: Open Web Text

Neuron 310 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: 1.9972. Min Range: -1.9972

Max Act: 1.9972. Min Act: -0.1700

Data Index: 2514196 (Open Web Text)

Max Activating Token Index: 191

Text #1

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.9685. Min Act: -0.1596

Data Index: 489375 (Open Web Text)

Max Activating Token Index: 646

Text #2

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.9806. Min Act: -0.1691

Data Index: 8813963 (Open Web Text)

Max Activating Token Index: 502

Text #3

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.9756. Min Act: -0.1578

Data Index: 4342004 (Open Web Text)

Max Activating Token Index: 394

Text #4

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.9760. Min Act: -0.1649

Data Index: 6990063 (Open Web Text)

Max Activating Token Index: 578

Text #5

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.9776. Min Act: -0.1691

Data Index: 1654037 (Open Web Text)

Max Activating Token Index: 785

Text #6

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.9721. Min Act: -0.1578

Data Index: 650297 (Open Web Text)

Max Activating Token Index: 197

Text #7

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.9779. Min Act: -0.1669

Data Index: 2667740 (Open Web Text)

Max Activating Token Index: 197

Text #8

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.9650. Min Act: -0.1698

Data Index: 4033058 (Open Web Text)

Max Activating Token Index: 438

Text #9

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.9494. Min Act: -0.1698

Data Index: 5100638 (Open Web Text)

Max Activating Token Index: 196

Text #10

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.9520. Min Act: -0.1642

Data Index: 5094546 (Open Web Text)

Max Activating Token Index: 577

Text #11

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.9522. Min Act: -0.1689

Data Index: 1961071 (Open Web Text)

Max Activating Token Index: 97

Text #12

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.9494. Min Act: -0.1630

Data Index: 2741453 (Open Web Text)

Max Activating Token Index: 721

Text #13

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.9630. Min Act: -0.1667

Data Index: 573572 (Open Web Text)

Max Activating Token Index: 481

Text #14

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.9529. Min Act: -0.1700

Data Index: 8727854 (Open Web Text)

Max Activating Token Index: 754

Text #15

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.9530. Min Act: -0.1694

Data Index: 4347151 (Open Web Text)

Max Activating Token Index: 384

Text #16

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.9625. Min Act: -0.1682

Data Index: 730153 (Open Web Text)

Max Activating Token Index: 646

Text #17

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.9635. Min Act: -0.1700

Data Index: 2319489 (Open Web Text)

Max Activating Token Index: 644

Text #18

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.9612. Min Act: -0.1684

Data Index: 4720533 (Open Web Text)

Max Activating Token Index: 820

Text #19

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.9283. Min Act: -0.1696

Data Index: 2312556 (Open Web Text)

Max Activating Token Index: 779