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

Dataset: Open Web Text

Neuron 2712 in Layer 6

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: 5.5376. Min Range: -5.5376

Max Act: 5.5376. Min Act: -0.1700

Data Index: 8630881 (Open Web Text)

Max Activating Token Index: 533

Text #1

Max Range: 5.5376. Min Range: -5.5376

Max Act: 5.4680. Min Act: -0.1700

Data Index: 1626642 (Open Web Text)

Max Activating Token Index: 52

Text #2

Max Range: 5.5376. Min Range: -5.5376

Max Act: 5.4578. Min Act: -0.1700

Data Index: 3823356 (Open Web Text)

Max Activating Token Index: 755

Text #3

Max Range: 5.5376. Min Range: -5.5376

Max Act: 5.4017. Min Act: -0.1700

Data Index: 4497153 (Open Web Text)

Max Activating Token Index: 842

Text #4

Max Range: 5.5376. Min Range: -5.5376

Max Act: 5.4353. Min Act: -0.1700

Data Index: 5107141 (Open Web Text)

Max Activating Token Index: 756

Text #5

Max Range: 5.5376. Min Range: -5.5376

Max Act: 5.4171. Min Act: -0.1700

Data Index: 2123071 (Open Web Text)

Max Activating Token Index: 861

Text #6

Max Range: 5.5376. Min Range: -5.5376

Max Act: 5.4090. Min Act: -0.1700

Data Index: 4562534 (Open Web Text)

Max Activating Token Index: 677

Text #7

Max Range: 5.5376. Min Range: -5.5376

Max Act: 5.4099. Min Act: -0.1700

Data Index: 547363 (Open Web Text)

Max Activating Token Index: 454

Text #8

Max Range: 5.5376. Min Range: -5.5376

Max Act: 5.3472. Min Act: -0.1700

Data Index: 4674806 (Open Web Text)

Max Activating Token Index: 539

Text #9

Max Range: 5.5376. Min Range: -5.5376

Max Act: 5.3313. Min Act: -0.1700

Data Index: 3284772 (Open Web Text)

Max Activating Token Index: 351

Text #10

Max Range: 5.5376. Min Range: -5.5376

Max Act: 5.3034. Min Act: -0.1700

Data Index: 4342303 (Open Web Text)

Max Activating Token Index: 386

Text #11

Max Range: 5.5376. Min Range: -5.5376

Max Act: 5.3136. Min Act: -0.1700

Data Index: 884421 (Open Web Text)

Max Activating Token Index: 969

Text #12

Max Range: 5.5376. Min Range: -5.5376

Max Act: 5.3326. Min Act: -0.1700

Data Index: 2802057 (Open Web Text)

Max Activating Token Index: 405

Text #13

Max Range: 5.5376. Min Range: -5.5376

Max Act: 5.3157. Min Act: -0.1700

Data Index: 2579422 (Open Web Text)

Max Activating Token Index: 84

Text #14

Max Range: 5.5376. Min Range: -5.5376

Max Act: 5.3032. Min Act: -0.1700

Data Index: 7264018 (Open Web Text)

Max Activating Token Index: 203

Text #15

Max Range: 5.5376. Min Range: -5.5376

Max Act: 5.2938. Min Act: -0.1700

Data Index: 7788366 (Open Web Text)

Max Activating Token Index: 757

Text #16

Max Range: 5.5376. Min Range: -5.5376

Max Act: 5.2688. Min Act: -0.1700

Data Index: 5557814 (Open Web Text)

Max Activating Token Index: 675

Text #17

Max Range: 5.5376. Min Range: -5.5376

Max Act: 5.2955. Min Act: -0.1700

Data Index: 5804519 (Open Web Text)

Max Activating Token Index: 356

Text #18

Max Range: 5.5376. Min Range: -5.5376

Max Act: 5.2824. Min Act: -0.1700

Data Index: 574785 (Open Web Text)

Max Activating Token Index: 266

Text #19

Max Range: 5.5376. Min Range: -5.5376

Max Act: 5.2776. Min Act: -0.1700

Data Index: 8519946 (Open Web Text)

Max Activating Token Index: 672