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

Dataset: Open Web Text

Neuron 813 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: 1.8756. Min Range: -1.8756

Max Act: 1.8756. Min Act: -0.1700

Data Index: 6738691 (Open Web Text)

Max Activating Token Index: 721

Text #1

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.6462. Min Act: -0.1700

Data Index: 8515197 (Open Web Text)

Max Activating Token Index: 442

Text #2

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.6355. Min Act: -0.1700

Data Index: 1037518 (Open Web Text)

Max Activating Token Index: 841

Text #3

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.6303. Min Act: -0.1700

Data Index: 1836251 (Open Web Text)

Max Activating Token Index: 319

Text #4

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.6137. Min Act: -0.1700

Data Index: 5697876 (Open Web Text)

Max Activating Token Index: 438

Text #5

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.6106. Min Act: -0.1700

Data Index: 7337454 (Open Web Text)

Max Activating Token Index: 366

Text #6

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.5902. Min Act: -0.1700

Data Index: 4995079 (Open Web Text)

Max Activating Token Index: 644

Text #7

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.5844. Min Act: -0.1699

Data Index: 4111023 (Open Web Text)

Max Activating Token Index: 922

Text #8

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.6011. Min Act: -0.1700

Data Index: 4995077 (Open Web Text)

Max Activating Token Index: 707

Text #9

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.5900. Min Act: -0.1698

Data Index: 3562913 (Open Web Text)

Max Activating Token Index: 826

Text #10

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.5931. Min Act: -0.1700

Data Index: 7886633 (Open Web Text)

Max Activating Token Index: 427

Text #11

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.6002. Min Act: -0.1700

Data Index: 8738012 (Open Web Text)

Max Activating Token Index: 444

Text #12

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.5907. Min Act: -0.1700

Data Index: 8042904 (Open Web Text)

Max Activating Token Index: 141

Text #13

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.5567. Min Act: -0.1700

Data Index: 4513320 (Open Web Text)

Max Activating Token Index: 509

Text #14

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.5783. Min Act: -0.1700

Data Index: 1836245 (Open Web Text)

Max Activating Token Index: 654

Text #15

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.5835. Min Act: -0.1700

Data Index: 2084242 (Open Web Text)

Max Activating Token Index: 682

Text #16

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.5857. Min Act: -0.1700

Data Index: 2817074 (Open Web Text)

Max Activating Token Index: 999

Text #17

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.5775. Min Act: -0.1700

Data Index: 1836248 (Open Web Text)

Max Activating Token Index: 949

Text #18

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.5862. Min Act: -0.1699

Data Index: 1836249 (Open Web Text)

Max Activating Token Index: 649

Text #19

Max Range: 1.8756. Min Range: -1.8756

Max Act: 1.5728. Min Act: -0.1584

Data Index: 8173730 (Open Web Text)

Max Activating Token Index: 916