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

Dataset: Open Web Text

Neuron 2608 in Layer 5

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: 3.8567. Min Range: -3.8567

Max Act: 3.8567. Min Act: -0.1700

Data Index: 8446308 (Open Web Text)

Max Activating Token Index: 326

Text #1

Max Range: 3.8567. Min Range: -3.8567

Max Act: 3.7839. Min Act: -0.1700

Data Index: 7433419 (Open Web Text)

Max Activating Token Index: 387

Text #2

Max Range: 3.8567. Min Range: -3.8567

Max Act: 3.7903. Min Act: -0.1700

Data Index: 8016082 (Open Web Text)

Max Activating Token Index: 430

Text #3

Max Range: 3.8567. Min Range: -3.8567

Max Act: 3.7840. Min Act: -0.1700

Data Index: 2739814 (Open Web Text)

Max Activating Token Index: 902

Text #4

Max Range: 3.8567. Min Range: -3.8567

Max Act: 3.7716. Min Act: -0.1700

Data Index: 698334 (Open Web Text)

Max Activating Token Index: 337

Text #5

Max Range: 3.8567. Min Range: -3.8567

Max Act: 3.7545. Min Act: -0.1700

Data Index: 5434927 (Open Web Text)

Max Activating Token Index: 820

Text #6

Max Range: 3.8567. Min Range: -3.8567

Max Act: 3.7342. Min Act: -0.1700

Data Index: 8812575 (Open Web Text)

Max Activating Token Index: 270

Text #7

Max Range: 3.8567. Min Range: -3.8567

Max Act: 3.7330. Min Act: -0.1700

Data Index: 2032831 (Open Web Text)

Max Activating Token Index: 717

Text #8

Max Range: 3.8567. Min Range: -3.8567

Max Act: 3.7390. Min Act: -0.1700

Data Index: 4096681 (Open Web Text)

Max Activating Token Index: 255

Text #9

Max Range: 3.8567. Min Range: -3.8567

Max Act: 3.7261. Min Act: -0.1700

Data Index: 4195621 (Open Web Text)

Max Activating Token Index: 437

Text #10

Max Range: 3.8567. Min Range: -3.8567

Max Act: 3.7143. Min Act: -0.1700

Data Index: 6860362 (Open Web Text)

Max Activating Token Index: 822

Text #11

Max Range: 3.8567. Min Range: -3.8567

Max Act: 3.7256. Min Act: -0.1700

Data Index: 3089453 (Open Web Text)

Max Activating Token Index: 773

Text #12

Max Range: 3.8567. Min Range: -3.8567

Max Act: 3.7229. Min Act: -0.1700

Data Index: 7909720 (Open Web Text)

Max Activating Token Index: 22

Text #13

Max Range: 3.8567. Min Range: -3.8567

Max Act: 3.7354. Min Act: -0.1700

Data Index: 4753629 (Open Web Text)

Max Activating Token Index: 309

Text #14

Max Range: 3.8567. Min Range: -3.8567

Max Act: 3.7025. Min Act: -0.1700

Data Index: 1502709 (Open Web Text)

Max Activating Token Index: 165

Text #15

Max Range: 3.8567. Min Range: -3.8567

Max Act: 3.7160. Min Act: -0.1700

Data Index: 8038365 (Open Web Text)

Max Activating Token Index: 421

Text #16

Max Range: 3.8567. Min Range: -3.8567

Max Act: 3.6973. Min Act: -0.1700

Data Index: 3609925 (Open Web Text)

Max Activating Token Index: 561

Text #17

Max Range: 3.8567. Min Range: -3.8567

Max Act: 3.7036. Min Act: -0.1700

Data Index: 5730661 (Open Web Text)

Max Activating Token Index: 672

Text #18

Max Range: 3.8567. Min Range: -3.8567

Max Act: 3.7012. Min Act: -0.1700

Data Index: 6777729 (Open Web Text)

Max Activating Token Index: 694

Text #19

Max Range: 3.8567. Min Range: -3.8567

Max Act: 3.6989. Min Act: -0.1700

Data Index: 3445431 (Open Web Text)

Max Activating Token Index: 356