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

Dataset: Open Web Text

Neuron 459 in Layer 4

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: 4.5025. Min Range: -4.5025

Max Act: 4.4837. Min Act: -0.1700

Data Index: 3591444 (Open Web Text)

Max Activating Token Index: 679

Text #1

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.5025. Min Act: -0.1700

Data Index: 1953129 (Open Web Text)

Max Activating Token Index: 155

Text #2

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.4707. Min Act: -0.1700

Data Index: 556018 (Open Web Text)

Max Activating Token Index: 126

Text #3

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.4673. Min Act: -0.1700

Data Index: 7544685 (Open Web Text)

Max Activating Token Index: 695

Text #4

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.4455. Min Act: -0.1700

Data Index: 3938930 (Open Web Text)

Max Activating Token Index: 341

Text #5

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.4639. Min Act: -0.1700

Data Index: 2354162 (Open Web Text)

Max Activating Token Index: 28

Text #6

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.4251. Min Act: -0.1700

Data Index: 255782 (Open Web Text)

Max Activating Token Index: 1003

Text #7

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.4350. Min Act: -0.1700

Data Index: 2477205 (Open Web Text)

Max Activating Token Index: 420

Text #8

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.4380. Min Act: -0.1700

Data Index: 8313932 (Open Web Text)

Max Activating Token Index: 307

Text #9

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.4200. Min Act: -0.1700

Data Index: 2227864 (Open Web Text)

Max Activating Token Index: 155

Text #10

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.4076. Min Act: -0.1700

Data Index: 624689 (Open Web Text)

Max Activating Token Index: 166

Text #11

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.4166. Min Act: -0.1700

Data Index: 3956381 (Open Web Text)

Max Activating Token Index: 528

Text #12

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.4375. Min Act: -0.1700

Data Index: 3114230 (Open Web Text)

Max Activating Token Index: 670

Text #13

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.4092. Min Act: -0.1700

Data Index: 3772570 (Open Web Text)

Max Activating Token Index: 464

Text #14

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.3978. Min Act: -0.1700

Data Index: 6063178 (Open Web Text)

Max Activating Token Index: 712

Text #15

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.3800. Min Act: -0.1700

Data Index: 1279849 (Open Web Text)

Max Activating Token Index: 390

Text #16

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.3754. Min Act: -0.1700

Data Index: 8455579 (Open Web Text)

Max Activating Token Index: 250

Text #17

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.3618. Min Act: -0.1700

Data Index: 2178158 (Open Web Text)

Max Activating Token Index: 527

Text #18

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.3554. Min Act: -0.1700

Data Index: 1967235 (Open Web Text)

Max Activating Token Index: 509

Text #19

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.3392. Min Act: -0.1700

Data Index: 6073952 (Open Web Text)

Max Activating Token Index: 263