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

Dataset: Open Web Text

Neuron 709 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: 3.9139. Min Range: -3.9139

Max Act: 3.9139. Min Act: -0.1700

Data Index: 3967412 (Open Web Text)

Max Activating Token Index: 557

Text #1

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.8918. Min Act: -0.1700

Data Index: 4949200 (Open Web Text)

Max Activating Token Index: 324

Text #2

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.8302. Min Act: -0.1700

Data Index: 1633031 (Open Web Text)

Max Activating Token Index: 363

Text #3

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.7850. Min Act: -0.1700

Data Index: 5585663 (Open Web Text)

Max Activating Token Index: 614

Text #4

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.7841. Min Act: -0.1700

Data Index: 278624 (Open Web Text)

Max Activating Token Index: 116

Text #5

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.7179. Min Act: -0.1700

Data Index: 2511454 (Open Web Text)

Max Activating Token Index: 531

Text #6

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.7465. Min Act: -0.1700

Data Index: 3458854 (Open Web Text)

Max Activating Token Index: 399

Text #7

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.7351. Min Act: -0.1700

Data Index: 4339534 (Open Web Text)

Max Activating Token Index: 601

Text #8

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.7303. Min Act: -0.1700

Data Index: 1301503 (Open Web Text)

Max Activating Token Index: 229

Text #9

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.7373. Min Act: -0.1700

Data Index: 6469503 (Open Web Text)

Max Activating Token Index: 555

Text #10

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.7259. Min Act: -0.1700

Data Index: 2157094 (Open Web Text)

Max Activating Token Index: 532

Text #11

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.7140. Min Act: -0.1700

Data Index: 7950944 (Open Web Text)

Max Activating Token Index: 447

Text #12

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.7016. Min Act: -0.1700

Data Index: 8823724 (Open Web Text)

Max Activating Token Index: 82

Text #13

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.7103. Min Act: -0.1700

Data Index: 8735334 (Open Web Text)

Max Activating Token Index: 175

Text #14

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.7095. Min Act: -0.1700

Data Index: 3807531 (Open Web Text)

Max Activating Token Index: 829

Text #15

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.6935. Min Act: -0.1700

Data Index: 1740616 (Open Web Text)

Max Activating Token Index: 616

Text #16

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.6661. Min Act: -0.1700

Data Index: 8573317 (Open Web Text)

Max Activating Token Index: 806

Text #17

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.6669. Min Act: -0.1700

Data Index: 3250428 (Open Web Text)

Max Activating Token Index: 328

Text #18

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.6582. Min Act: -0.1700

Data Index: 7502682 (Open Web Text)

Max Activating Token Index: 401

Text #19

Max Range: 3.9139. Min Range: -3.9139

Max Act: 3.6576. Min Act: -0.1700

Data Index: 1740391 (Open Web Text)

Max Activating Token Index: 661