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

Dataset: Open Web Text

Neuron 514 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: 4.4741. Min Range: -4.4741

Max Act: 4.4686. Min Act: -0.1700

Data Index: 8467891 (Open Web Text)

Max Activating Token Index: 485

Text #1

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.4629. Min Act: -0.1700

Data Index: 5286202 (Open Web Text)

Max Activating Token Index: 850

Text #2

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.4668. Min Act: -0.1700

Data Index: 5575336 (Open Web Text)

Max Activating Token Index: 146

Text #3

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.4741. Min Act: -0.1700

Data Index: 150218 (Open Web Text)

Max Activating Token Index: 794

Text #4

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.4595. Min Act: -0.1700

Data Index: 4468475 (Open Web Text)

Max Activating Token Index: 23

Text #5

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.4548. Min Act: -0.1700

Data Index: 3095831 (Open Web Text)

Max Activating Token Index: 893

Text #6

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.4311. Min Act: -0.1700

Data Index: 7702249 (Open Web Text)

Max Activating Token Index: 125

Text #7

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.4224. Min Act: -0.1700

Data Index: 1993030 (Open Web Text)

Max Activating Token Index: 340

Text #8

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.4412. Min Act: -0.1700

Data Index: 6970971 (Open Web Text)

Max Activating Token Index: 128

Text #9

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.4334. Min Act: -0.1700

Data Index: 8568918 (Open Web Text)

Max Activating Token Index: 823

Text #10

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.3938. Min Act: -0.1700

Data Index: 8682739 (Open Web Text)

Max Activating Token Index: 44

Text #11

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.3951. Min Act: -0.1700

Data Index: 10752 (Open Web Text)

Max Activating Token Index: 232

Text #12

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.4169. Min Act: -0.1700

Data Index: 2994059 (Open Web Text)

Max Activating Token Index: 437

Text #13

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.4065. Min Act: -0.1700

Data Index: 6697935 (Open Web Text)

Max Activating Token Index: 634

Text #14

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.4072. Min Act: -0.1700

Data Index: 3794868 (Open Web Text)

Max Activating Token Index: 409

Text #15

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.3661. Min Act: -0.1700

Data Index: 8632938 (Open Web Text)

Max Activating Token Index: 678

Text #16

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.3640. Min Act: -0.1700

Data Index: 875683 (Open Web Text)

Max Activating Token Index: 161

Text #17

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.3550. Min Act: -0.1700

Data Index: 6473922 (Open Web Text)

Max Activating Token Index: 663

Text #18

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.3478. Min Act: -0.1700

Data Index: 3373402 (Open Web Text)

Max Activating Token Index: 822

Text #19

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.3481. Min Act: -0.1700

Data Index: 5314790 (Open Web Text)

Max Activating Token Index: 359