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

Dataset: Open Web Text

Neuron 2048 in Layer 6

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: 4.5827. Min Range: -4.5827

Max Act: 4.5827. Min Act: -0.1700

Data Index: 4307455 (Open Web Text)

Max Activating Token Index: 292

Text #1

Max Range: 4.5827. Min Range: -4.5827

Max Act: 4.4572. Min Act: -0.1700

Data Index: 4148061 (Open Web Text)

Max Activating Token Index: 566

Text #2

Max Range: 4.5827. Min Range: -4.5827

Max Act: 4.3918. Min Act: -0.1700

Data Index: 7887871 (Open Web Text)

Max Activating Token Index: 117

Text #3

Max Range: 4.5827. Min Range: -4.5827

Max Act: 4.3267. Min Act: -0.1700

Data Index: 4138786 (Open Web Text)

Max Activating Token Index: 530

Text #4

Max Range: 4.5827. Min Range: -4.5827

Max Act: 4.2957. Min Act: -0.1700

Data Index: 4763723 (Open Web Text)

Max Activating Token Index: 383

Text #5

Max Range: 4.5827. Min Range: -4.5827

Max Act: 4.2749. Min Act: -0.1700

Data Index: 2900238 (Open Web Text)

Max Activating Token Index: 117

Text #6

Max Range: 4.5827. Min Range: -4.5827

Max Act: 4.2606. Min Act: -0.1700

Data Index: 8585831 (Open Web Text)

Max Activating Token Index: 70

Text #7

Max Range: 4.5827. Min Range: -4.5827

Max Act: 4.2613. Min Act: -0.1700

Data Index: 5569984 (Open Web Text)

Max Activating Token Index: 472

Text #8

Max Range: 4.5827. Min Range: -4.5827

Max Act: 4.1996. Min Act: -0.1700

Data Index: 2639400 (Open Web Text)

Max Activating Token Index: 516

Text #9

Max Range: 4.5827. Min Range: -4.5827

Max Act: 4.1834. Min Act: -0.1700

Data Index: 7360076 (Open Web Text)

Max Activating Token Index: 273

Text #10

Max Range: 4.5827. Min Range: -4.5827

Max Act: 4.2017. Min Act: -0.1700

Data Index: 5346636 (Open Web Text)

Max Activating Token Index: 938

Text #11

Max Range: 4.5827. Min Range: -4.5827

Max Act: 4.1566. Min Act: -0.1700

Data Index: 6403885 (Open Web Text)

Max Activating Token Index: 980

Text #12

Max Range: 4.5827. Min Range: -4.5827

Max Act: 4.1226. Min Act: -0.1700

Data Index: 1181919 (Open Web Text)

Max Activating Token Index: 1010

Text #13

Max Range: 4.5827. Min Range: -4.5827

Max Act: 4.1452. Min Act: -0.1700

Data Index: 5604352 (Open Web Text)

Max Activating Token Index: 109

Text #14

Max Range: 4.5827. Min Range: -4.5827

Max Act: 4.1182. Min Act: -0.1700

Data Index: 4029997 (Open Web Text)

Max Activating Token Index: 866

Text #15

Max Range: 4.5827. Min Range: -4.5827

Max Act: 4.1513. Min Act: -0.1700

Data Index: 2754522 (Open Web Text)

Max Activating Token Index: 574

Text #16

Max Range: 4.5827. Min Range: -4.5827

Max Act: 4.1334. Min Act: -0.1700

Data Index: 8052098 (Open Web Text)

Max Activating Token Index: 431

Text #17

Max Range: 4.5827. Min Range: -4.5827

Max Act: 4.1318. Min Act: -0.1700

Data Index: 6862181 (Open Web Text)

Max Activating Token Index: 947

Text #18

Max Range: 4.5827. Min Range: -4.5827

Max Act: 4.1516. Min Act: -0.1700

Data Index: 4470580 (Open Web Text)

Max Activating Token Index: 747

Text #19

Max Range: 4.5827. Min Range: -4.5827

Max Act: 4.0876. Min Act: -0.1700

Data Index: 7852376 (Open Web Text)

Max Activating Token Index: 1021