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

Dataset: Open Web Text

Neuron 647 in Layer 5

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: 4.6856. Min Range: -4.6856

Max Act: 4.6856. Min Act: -0.1700

Data Index: 3866453 (Open Web Text)

Max Activating Token Index: 572

Text #1

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.4753. Min Act: -0.1700

Data Index: 5692707 (Open Web Text)

Max Activating Token Index: 233

Text #2

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.3945. Min Act: -0.1700

Data Index: 8713051 (Open Web Text)

Max Activating Token Index: 295

Text #3

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.4209. Min Act: -0.1700

Data Index: 7617565 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.4167. Min Act: -0.1700

Data Index: 2447128 (Open Web Text)

Max Activating Token Index: 701

Text #5

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.3974. Min Act: -0.1700

Data Index: 4041236 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.3604. Min Act: -0.1700

Data Index: 4368348 (Open Web Text)

Max Activating Token Index: 717

Text #7

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.3580. Min Act: -0.1700

Data Index: 3139528 (Open Web Text)

Max Activating Token Index: 71

Text #8

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.3530. Min Act: -0.1700

Data Index: 298253 (Open Web Text)

Max Activating Token Index: 734

Text #9

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.3510. Min Act: -0.1700

Data Index: 5949566 (Open Web Text)

Max Activating Token Index: 926

Text #10

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.3406. Min Act: -0.1700

Data Index: 8310727 (Open Web Text)

Max Activating Token Index: 804

Text #11

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.3038. Min Act: -0.1700

Data Index: 7502757 (Open Web Text)

Max Activating Token Index: 745

Text #12

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.2952. Min Act: -0.1700

Data Index: 2447639 (Open Web Text)

Max Activating Token Index: 94

Text #13

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.3069. Min Act: -0.1700

Data Index: 42570 (Open Web Text)

Max Activating Token Index: 21

Text #14

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.3048. Min Act: -0.1700

Data Index: 8609602 (Open Web Text)

Max Activating Token Index: 395

Text #15

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.3282. Min Act: -0.1700

Data Index: 3195727 (Open Web Text)

Max Activating Token Index: 367

Text #16

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.2881. Min Act: -0.1700

Data Index: 4154075 (Open Web Text)

Max Activating Token Index: 966

Text #17

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.2517. Min Act: -0.1700

Data Index: 5961156 (Open Web Text)

Max Activating Token Index: 557

Text #18

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.2893. Min Act: -0.1700

Data Index: 8707141 (Open Web Text)

Max Activating Token Index: 794

Text #19

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.2519. Min Act: -0.1700

Data Index: 1296314 (Open Web Text)

Max Activating Token Index: 261