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

Dataset: Open Web Text

Neuron 2570 in Layer 3

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: 4.1819. Min Range: -4.1819

Max Act: 4.1819. Min Act: -0.1700

Data Index: 507877 (Open Web Text)

Max Activating Token Index: 281

Text #1

Max Range: 4.1819. Min Range: -4.1819

Max Act: 4.0510. Min Act: -0.1700

Data Index: 6639000 (Open Web Text)

Max Activating Token Index: 491

Text #2

Max Range: 4.1819. Min Range: -4.1819

Max Act: 4.0142. Min Act: -0.1700

Data Index: 858684 (Open Web Text)

Max Activating Token Index: 50

Text #3

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.9390. Min Act: -0.1700

Data Index: 259306 (Open Web Text)

Max Activating Token Index: 870

Text #4

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.9326. Min Act: -0.1700

Data Index: 2203101 (Open Web Text)

Max Activating Token Index: 357

Text #5

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.9216. Min Act: -0.1700

Data Index: 928570 (Open Web Text)

Max Activating Token Index: 509

Text #6

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.8959. Min Act: -0.1700

Data Index: 6266829 (Open Web Text)

Max Activating Token Index: 758

Text #7

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.8802. Min Act: -0.1700

Data Index: 6266827 (Open Web Text)

Max Activating Token Index: 279

Text #8

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.9113. Min Act: -0.1700

Data Index: 1229846 (Open Web Text)

Max Activating Token Index: 498

Text #9

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.9173. Min Act: -0.1700

Data Index: 2048812 (Open Web Text)

Max Activating Token Index: 282

Text #10

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.8593. Min Act: -0.1700

Data Index: 7498156 (Open Web Text)

Max Activating Token Index: 957

Text #11

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.9137. Min Act: -0.1700

Data Index: 5470044 (Open Web Text)

Max Activating Token Index: 826

Text #12

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.8190. Min Act: -0.1700

Data Index: 8794899 (Open Web Text)

Max Activating Token Index: 511

Text #13

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.8620. Min Act: -0.1700

Data Index: 5592442 (Open Web Text)

Max Activating Token Index: 611

Text #14

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.8699. Min Act: -0.1700

Data Index: 5356243 (Open Web Text)

Max Activating Token Index: 55

Text #15

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.8514. Min Act: -0.1700

Data Index: 7969192 (Open Web Text)

Max Activating Token Index: 688

Text #16

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.8904. Min Act: -0.1700

Data Index: 7402387 (Open Web Text)

Max Activating Token Index: 66

Text #17

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.8688. Min Act: -0.1700

Data Index: 6331623 (Open Web Text)

Max Activating Token Index: 217

Text #18

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.8576. Min Act: -0.1700

Data Index: 2503566 (Open Web Text)

Max Activating Token Index: 375

Text #19

Max Range: 4.1819. Min Range: -4.1819

Max Act: 3.8702. Min Act: -0.1700

Data Index: 1130831 (Open Web Text)

Max Activating Token Index: 813