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

Dataset: Open Web Text

Neuron 545 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: 2.4465. Min Range: -2.4465

Max Act: 2.4415. Min Act: -0.1700

Data Index: 7877151 (Open Web Text)

Max Activating Token Index: 1016

Text #1

Max Range: 2.4465. Min Range: -2.4465

Max Act: 2.4465. Min Act: -0.1700

Data Index: 6287620 (Open Web Text)

Max Activating Token Index: 453

Text #2

Max Range: 2.4465. Min Range: -2.4465

Max Act: 2.4173. Min Act: -0.1700

Data Index: 8095635 (Open Web Text)

Max Activating Token Index: 371

Text #3

Max Range: 2.4465. Min Range: -2.4465

Max Act: 2.4019. Min Act: -0.1700

Data Index: 2765289 (Open Web Text)

Max Activating Token Index: 373

Text #4

Max Range: 2.4465. Min Range: -2.4465

Max Act: 2.3900. Min Act: -0.1700

Data Index: 2533686 (Open Web Text)

Max Activating Token Index: 453

Text #5

Max Range: 2.4465. Min Range: -2.4465

Max Act: 2.3749. Min Act: -0.1700

Data Index: 4823674 (Open Web Text)

Max Activating Token Index: 285

Text #6

Max Range: 2.4465. Min Range: -2.4465

Max Act: 2.3659. Min Act: -0.1700

Data Index: 6825383 (Open Web Text)

Max Activating Token Index: 631

Text #7

Max Range: 2.4465. Min Range: -2.4465

Max Act: 2.3845. Min Act: -0.1700

Data Index: 7759776 (Open Web Text)

Max Activating Token Index: 936

Text #8

Max Range: 2.4465. Min Range: -2.4465

Max Act: 2.3839. Min Act: -0.1700

Data Index: 6844026 (Open Web Text)

Max Activating Token Index: 884

Text #9

Max Range: 2.4465. Min Range: -2.4465

Max Act: 2.3458. Min Act: -0.1700

Data Index: 4123726 (Open Web Text)

Max Activating Token Index: 474

Text #10

Max Range: 2.4465. Min Range: -2.4465

Max Act: 2.3433. Min Act: -0.1700

Data Index: 3582735 (Open Web Text)

Max Activating Token Index: 214

Text #11

Max Range: 2.4465. Min Range: -2.4465

Max Act: 2.3796. Min Act: -0.1700

Data Index: 2351875 (Open Web Text)

Max Activating Token Index: 1001

Text #12

Max Range: 2.4465. Min Range: -2.4465

Max Act: 2.3473. Min Act: -0.1700

Data Index: 4150577 (Open Web Text)

Max Activating Token Index: 559

Text #13

Max Range: 2.4465. Min Range: -2.4465

Max Act: 2.3480. Min Act: -0.1700

Data Index: 8107768 (Open Web Text)

Max Activating Token Index: 295

Text #14

Max Range: 2.4465. Min Range: -2.4465

Max Act: 2.3602. Min Act: -0.1700

Data Index: 3859036 (Open Web Text)

Max Activating Token Index: 651

Text #15

Max Range: 2.4465. Min Range: -2.4465

Max Act: 2.3520. Min Act: -0.1700

Data Index: 6018548 (Open Web Text)

Max Activating Token Index: 812

Text #16

Max Range: 2.4465. Min Range: -2.4465

Max Act: 2.3476. Min Act: -0.1700

Data Index: 6298958 (Open Web Text)

Max Activating Token Index: 1000

Text #17

Max Range: 2.4465. Min Range: -2.4465

Max Act: 2.3273. Min Act: -0.1700

Data Index: 5917041 (Open Web Text)

Max Activating Token Index: 751

Text #18

Max Range: 2.4465. Min Range: -2.4465

Max Act: 2.3548. Min Act: -0.1700

Data Index: 419799 (Open Web Text)

Max Activating Token Index: 864

Text #19

Max Range: 2.4465. Min Range: -2.4465

Max Act: 2.3497. Min Act: -0.1700

Data Index: 3473888 (Open Web Text)

Max Activating Token Index: 891