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

Dataset: Open Web Text

Neuron 2305 in Layer 2

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: 4.4797. Min Range: -4.4797

Max Act: 4.4797. Min Act: -0.1700

Data Index: 3890415 (Open Web Text)

Max Activating Token Index: 831

Text #1

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.4313. Min Act: -0.1700

Data Index: 6982451 (Open Web Text)

Max Activating Token Index: 1017

Text #2

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.4610. Min Act: -0.1700

Data Index: 2230994 (Open Web Text)

Max Activating Token Index: 171

Text #3

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.4051. Min Act: -0.1700

Data Index: 8508019 (Open Web Text)

Max Activating Token Index: 424

Text #4

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.4197. Min Act: -0.1700

Data Index: 7922553 (Open Web Text)

Max Activating Token Index: 143

Text #5

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.4105. Min Act: -0.1700

Data Index: 7637146 (Open Web Text)

Max Activating Token Index: 467

Text #6

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.3882. Min Act: -0.1700

Data Index: 1875158 (Open Web Text)

Max Activating Token Index: 252

Text #7

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.3689. Min Act: -0.1700

Data Index: 3926418 (Open Web Text)

Max Activating Token Index: 551

Text #8

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.3995. Min Act: -0.1700

Data Index: 2828414 (Open Web Text)

Max Activating Token Index: 53

Text #9

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.3951. Min Act: -0.1700

Data Index: 7623153 (Open Web Text)

Max Activating Token Index: 394

Text #10

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.3470. Min Act: -0.1700

Data Index: 8641890 (Open Web Text)

Max Activating Token Index: 207

Text #11

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.3760. Min Act: -0.1700

Data Index: 248430 (Open Web Text)

Max Activating Token Index: 420

Text #12

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.3531. Min Act: -0.1700

Data Index: 5867939 (Open Web Text)

Max Activating Token Index: 382

Text #13

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.4002. Min Act: -0.1700

Data Index: 5789166 (Open Web Text)

Max Activating Token Index: 600

Text #14

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.3377. Min Act: -0.1700

Data Index: 57920 (Open Web Text)

Max Activating Token Index: 637

Text #15

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.3072. Min Act: -0.1700

Data Index: 2068820 (Open Web Text)

Max Activating Token Index: 381

Text #16

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.3503. Min Act: -0.1700

Data Index: 778204 (Open Web Text)

Max Activating Token Index: 905

Text #17

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.3077. Min Act: -0.1700

Data Index: 6243537 (Open Web Text)

Max Activating Token Index: 623

Text #18

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.3314. Min Act: -0.1700

Data Index: 460167 (Open Web Text)

Max Activating Token Index: 555

Text #19

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.3423. Min Act: -0.1700

Data Index: 3925003 (Open Web Text)

Max Activating Token Index: 863