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

Dataset: Open Web Text

Neuron 2230 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: 3.2117. Min Range: -3.2117

Max Act: 3.2117. Min Act: -0.1700

Data Index: 451836 (Open Web Text)

Max Activating Token Index: 620

Text #1

Max Range: 3.2117. Min Range: -3.2117

Max Act: 3.1482. Min Act: -0.1700

Data Index: 606082 (Open Web Text)

Max Activating Token Index: 534

Text #2

Max Range: 3.2117. Min Range: -3.2117

Max Act: 3.1168. Min Act: -0.1700

Data Index: 4096875 (Open Web Text)

Max Activating Token Index: 968

Text #3

Max Range: 3.2117. Min Range: -3.2117

Max Act: 3.0976. Min Act: -0.1700

Data Index: 6052229 (Open Web Text)

Max Activating Token Index: 542

Text #4

Max Range: 3.2117. Min Range: -3.2117

Max Act: 3.0916. Min Act: -0.1700

Data Index: 2338552 (Open Web Text)

Max Activating Token Index: 613

Text #5

Max Range: 3.2117. Min Range: -3.2117

Max Act: 3.0581. Min Act: -0.1700

Data Index: 792960 (Open Web Text)

Max Activating Token Index: 265

Text #6

Max Range: 3.2117. Min Range: -3.2117

Max Act: 3.0533. Min Act: -0.1700

Data Index: 2895438 (Open Web Text)

Max Activating Token Index: 950

Text #7

Max Range: 3.2117. Min Range: -3.2117

Max Act: 3.0447. Min Act: -0.1700

Data Index: 6194604 (Open Web Text)

Max Activating Token Index: 659

Text #8

Max Range: 3.2117. Min Range: -3.2117

Max Act: 2.9950. Min Act: -0.1700

Data Index: 8297037 (Open Web Text)

Max Activating Token Index: 481

Text #9

Max Range: 3.2117. Min Range: -3.2117

Max Act: 3.0098. Min Act: -0.1700

Data Index: 897699 (Open Web Text)

Max Activating Token Index: 759

Text #10

Max Range: 3.2117. Min Range: -3.2117

Max Act: 3.0024. Min Act: -0.1700

Data Index: 1782413 (Open Web Text)

Max Activating Token Index: 916

Text #11

Max Range: 3.2117. Min Range: -3.2117

Max Act: 2.9841. Min Act: -0.1700

Data Index: 407693 (Open Web Text)

Max Activating Token Index: 245

Text #12

Max Range: 3.2117. Min Range: -3.2117

Max Act: 2.9735. Min Act: -0.1700

Data Index: 2924297 (Open Web Text)

Max Activating Token Index: 275

Text #13

Max Range: 3.2117. Min Range: -3.2117

Max Act: 2.9832. Min Act: -0.1700

Data Index: 5246876 (Open Web Text)

Max Activating Token Index: 201

Text #14

Max Range: 3.2117. Min Range: -3.2117

Max Act: 2.9766. Min Act: -0.1700

Data Index: 1842874 (Open Web Text)

Max Activating Token Index: 727

Text #15

Max Range: 3.2117. Min Range: -3.2117

Max Act: 2.9771. Min Act: -0.1700

Data Index: 4322691 (Open Web Text)

Max Activating Token Index: 991

Text #16

Max Range: 3.2117. Min Range: -3.2117

Max Act: 2.9910. Min Act: -0.1700

Data Index: 8569253 (Open Web Text)

Max Activating Token Index: 339

Text #17

Max Range: 3.2117. Min Range: -3.2117

Max Act: 2.9631. Min Act: -0.1700

Data Index: 5624108 (Open Web Text)

Max Activating Token Index: 794

Text #18

Max Range: 3.2117. Min Range: -3.2117

Max Act: 2.9815. Min Act: -0.1700

Data Index: 4262788 (Open Web Text)

Max Activating Token Index: 443

Text #19

Max Range: 3.2117. Min Range: -3.2117

Max Act: 2.9799. Min Act: -0.1700

Data Index: 402500 (Open Web Text)

Max Activating Token Index: 935