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

Dataset: Open Web Text

Neuron 639 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: 3.5160. Min Range: -3.5160

Max Act: 3.5082. Min Act: -0.1700

Data Index: 2877424 (Open Web Text)

Max Activating Token Index: 578

Text #1

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.5160. Min Act: -0.1700

Data Index: 1618848 (Open Web Text)

Max Activating Token Index: 1009

Text #2

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.4460. Min Act: -0.1700

Data Index: 4050191 (Open Web Text)

Max Activating Token Index: 89

Text #3

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.4412. Min Act: -0.1700

Data Index: 7544950 (Open Web Text)

Max Activating Token Index: 447

Text #4

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.4131. Min Act: -0.1700

Data Index: 6999350 (Open Web Text)

Max Activating Token Index: 192

Text #5

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.3588. Min Act: -0.1700

Data Index: 6247069 (Open Web Text)

Max Activating Token Index: 604

Text #6

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.3729. Min Act: -0.1700

Data Index: 217870 (Open Web Text)

Max Activating Token Index: 507

Text #7

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.3462. Min Act: -0.1700

Data Index: 8376048 (Open Web Text)

Max Activating Token Index: 493

Text #8

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.3001. Min Act: -0.1700

Data Index: 6391321 (Open Web Text)

Max Activating Token Index: 599

Text #9

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.2914. Min Act: -0.1700

Data Index: 6096297 (Open Web Text)

Max Activating Token Index: 820

Text #10

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.2778. Min Act: -0.1700

Data Index: 8624053 (Open Web Text)

Max Activating Token Index: 738

Text #11

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.2624. Min Act: -0.1700

Data Index: 6615369 (Open Web Text)

Max Activating Token Index: 1009

Text #12

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.2990. Min Act: -0.1700

Data Index: 6248548 (Open Web Text)

Max Activating Token Index: 69

Text #13

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.3135. Min Act: -0.1700

Data Index: 5905081 (Open Web Text)

Max Activating Token Index: 875

Text #14

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.2494. Min Act: -0.1700

Data Index: 7254392 (Open Web Text)

Max Activating Token Index: 637

Text #15

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.2665. Min Act: -0.1700

Data Index: 6267744 (Open Web Text)

Max Activating Token Index: 588

Text #16

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.2956. Min Act: -0.1700

Data Index: 7757071 (Open Web Text)

Max Activating Token Index: 804

Text #17

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.2885. Min Act: -0.1700

Data Index: 3864153 (Open Web Text)

Max Activating Token Index: 737

Text #18

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.2782. Min Act: -0.1700

Data Index: 7263194 (Open Web Text)

Max Activating Token Index: 574

Text #19

Max Range: 3.5160. Min Range: -3.5160

Max Act: 3.2446. Min Act: -0.1700

Data Index: 8798889 (Open Web Text)

Max Activating Token Index: 825