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

Dataset: Open Web Text

Neuron 1095 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: 4.6171. Min Range: -4.6171

Max Act: 4.6171. Min Act: -0.1700

Data Index: 7838373 (Open Web Text)

Max Activating Token Index: 622

Text #1

Max Range: 4.6171. Min Range: -4.6171

Max Act: 4.5197. Min Act: -0.1700

Data Index: 8126853 (Open Web Text)

Max Activating Token Index: 758

Text #2

Max Range: 4.6171. Min Range: -4.6171

Max Act: 4.5007. Min Act: -0.1700

Data Index: 4131217 (Open Web Text)

Max Activating Token Index: 769

Text #3

Max Range: 4.6171. Min Range: -4.6171

Max Act: 4.4809. Min Act: -0.1700

Data Index: 290523 (Open Web Text)

Max Activating Token Index: 219

Text #4

Max Range: 4.6171. Min Range: -4.6171

Max Act: 4.4302. Min Act: -0.1700

Data Index: 8379214 (Open Web Text)

Max Activating Token Index: 370

Text #5

Max Range: 4.6171. Min Range: -4.6171

Max Act: 4.4383. Min Act: -0.1700

Data Index: 1955147 (Open Web Text)

Max Activating Token Index: 673

Text #6

Max Range: 4.6171. Min Range: -4.6171

Max Act: 4.3972. Min Act: -0.1700

Data Index: 6610054 (Open Web Text)

Max Activating Token Index: 570

Text #7

Max Range: 4.6171. Min Range: -4.6171

Max Act: 4.4251. Min Act: -0.1700

Data Index: 5687003 (Open Web Text)

Max Activating Token Index: 750

Text #8

Max Range: 4.6171. Min Range: -4.6171

Max Act: 4.3967. Min Act: -0.1700

Data Index: 5596895 (Open Web Text)

Max Activating Token Index: 149

Text #9

Max Range: 4.6171. Min Range: -4.6171

Max Act: 4.3620. Min Act: -0.1700

Data Index: 5158484 (Open Web Text)

Max Activating Token Index: 785

Text #10

Max Range: 4.6171. Min Range: -4.6171

Max Act: 4.3797. Min Act: -0.1700

Data Index: 4817730 (Open Web Text)

Max Activating Token Index: 154

Text #11

Max Range: 4.6171. Min Range: -4.6171

Max Act: 4.3908. Min Act: -0.1700

Data Index: 2919515 (Open Web Text)

Max Activating Token Index: 573

Text #12

Max Range: 4.6171. Min Range: -4.6171

Max Act: 4.3813. Min Act: -0.1700

Data Index: 5800365 (Open Web Text)

Max Activating Token Index: 298

Text #13

Max Range: 4.6171. Min Range: -4.6171

Max Act: 4.3390. Min Act: -0.1700

Data Index: 7274081 (Open Web Text)

Max Activating Token Index: 668

Text #14

Max Range: 4.6171. Min Range: -4.6171

Max Act: 4.4171. Min Act: -0.1700

Data Index: 3352443 (Open Web Text)

Max Activating Token Index: 876

Text #15

Max Range: 4.6171. Min Range: -4.6171

Max Act: 4.3722. Min Act: -0.1700

Data Index: 3619280 (Open Web Text)

Max Activating Token Index: 579

Text #16

Max Range: 4.6171. Min Range: -4.6171

Max Act: 4.3362. Min Act: -0.1700

Data Index: 215015 (Open Web Text)

Max Activating Token Index: 200

Text #17

Max Range: 4.6171. Min Range: -4.6171

Max Act: 4.3183. Min Act: -0.1700

Data Index: 4259108 (Open Web Text)

Max Activating Token Index: 679

Text #18

Max Range: 4.6171. Min Range: -4.6171

Max Act: 4.2980. Min Act: -0.1700

Data Index: 5800370 (Open Web Text)

Max Activating Token Index: 681

Text #19

Max Range: 4.6171. Min Range: -4.6171

Max Act: 4.2569. Min Act: -0.1700

Data Index: 5983157 (Open Web Text)

Max Activating Token Index: 624