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

Dataset: Open Web Text

Neuron 1052 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: 4.6704. Min Range: -4.6704

Max Act: 4.6704. Min Act: -0.1700

Data Index: 4674248 (Open Web Text)

Max Activating Token Index: 249

Text #1

Max Range: 4.6704. Min Range: -4.6704

Max Act: 4.5902. Min Act: -0.1700

Data Index: 7295605 (Open Web Text)

Max Activating Token Index: 1002

Text #2

Max Range: 4.6704. Min Range: -4.6704

Max Act: 4.5475. Min Act: -0.1700

Data Index: 7894013 (Open Web Text)

Max Activating Token Index: 947

Text #3

Max Range: 4.6704. Min Range: -4.6704

Max Act: 4.4898. Min Act: -0.1700

Data Index: 4305353 (Open Web Text)

Max Activating Token Index: 572

Text #4

Max Range: 4.6704. Min Range: -4.6704

Max Act: 4.4752. Min Act: -0.1700

Data Index: 3137927 (Open Web Text)

Max Activating Token Index: 457

Text #5

Max Range: 4.6704. Min Range: -4.6704

Max Act: 4.4602. Min Act: -0.1700

Data Index: 7916621 (Open Web Text)

Max Activating Token Index: 359

Text #6

Max Range: 4.6704. Min Range: -4.6704

Max Act: 4.4781. Min Act: -0.1700

Data Index: 6775564 (Open Web Text)

Max Activating Token Index: 641

Text #7

Max Range: 4.6704. Min Range: -4.6704

Max Act: 4.4531. Min Act: -0.1700

Data Index: 8664621 (Open Web Text)

Max Activating Token Index: 58

Text #8

Max Range: 4.6704. Min Range: -4.6704

Max Act: 4.4166. Min Act: -0.1700

Data Index: 134125 (Open Web Text)

Max Activating Token Index: 699

Text #9

Max Range: 4.6704. Min Range: -4.6704

Max Act: 4.4007. Min Act: -0.1700

Data Index: 8053971 (Open Web Text)

Max Activating Token Index: 593

Text #10

Max Range: 4.6704. Min Range: -4.6704

Max Act: 4.3669. Min Act: -0.1700

Data Index: 77288 (Open Web Text)

Max Activating Token Index: 786

Text #11

Max Range: 4.6704. Min Range: -4.6704

Max Act: 4.3702. Min Act: -0.1700

Data Index: 5089764 (Open Web Text)

Max Activating Token Index: 665

Text #12

Max Range: 4.6704. Min Range: -4.6704

Max Act: 4.3559. Min Act: -0.1700

Data Index: 3171508 (Open Web Text)

Max Activating Token Index: 783

Text #13

Max Range: 4.6704. Min Range: -4.6704

Max Act: 4.3164. Min Act: -0.1700

Data Index: 6561319 (Open Web Text)

Max Activating Token Index: 668

Text #14

Max Range: 4.6704. Min Range: -4.6704

Max Act: 4.2901. Min Act: -0.1700

Data Index: 4457812 (Open Web Text)

Max Activating Token Index: 664

Text #15

Max Range: 4.6704. Min Range: -4.6704

Max Act: 4.2881. Min Act: -0.1700

Data Index: 4021144 (Open Web Text)

Max Activating Token Index: 940

Text #16

Max Range: 4.6704. Min Range: -4.6704

Max Act: 4.3047. Min Act: -0.1700

Data Index: 4904232 (Open Web Text)

Max Activating Token Index: 878

Text #17

Max Range: 4.6704. Min Range: -4.6704

Max Act: 4.2794. Min Act: -0.1700

Data Index: 5887689 (Open Web Text)

Max Activating Token Index: 641

Text #18

Max Range: 4.6704. Min Range: -4.6704

Max Act: 4.2794. Min Act: -0.1700

Data Index: 7098081 (Open Web Text)

Max Activating Token Index: 505

Text #19

Max Range: 4.6704. Min Range: -4.6704

Max Act: 4.3036. Min Act: -0.1700

Data Index: 418503 (Open Web Text)

Max Activating Token Index: 614