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

Dataset: Open Web Text

Neuron 2729 in Layer 0

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: 3.3033. Min Range: -3.3033

Max Act: 3.3033. Min Act: -0.1700

Data Index: 5736451 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.2827. Min Act: -0.1700

Data Index: 7109691 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.2890. Min Act: -0.1700

Data Index: 2462131 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.2693. Min Act: -0.1700

Data Index: 1202169 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.2491. Min Act: -0.1700

Data Index: 7510556 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.2565. Min Act: -0.1700

Data Index: 7603442 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.2544. Min Act: -0.1700

Data Index: 6202404 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.2541. Min Act: -0.1700

Data Index: 504440 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.2528. Min Act: -0.1700

Data Index: 2634455 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.2627. Min Act: -0.1700

Data Index: 6357645 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.2313. Min Act: -0.1700

Data Index: 8372327 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.2447. Min Act: -0.1700

Data Index: 5271413 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.2376. Min Act: -0.1700

Data Index: 4407428 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.2186. Min Act: -0.1700

Data Index: 4540567 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.2223. Min Act: -0.1700

Data Index: 4989016 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.2265. Min Act: -0.1700

Data Index: 3001844 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.2050. Min Act: -0.1700

Data Index: 2187620 (Open Web Text)

Max Activating Token Index: 22

Text #17

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.1820. Min Act: -0.1700

Data Index: 5728193 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.1977. Min Act: -0.1700

Data Index: 6161294 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.1958. Min Act: -0.1700

Data Index: 2211285 (Open Web Text)

Max Activating Token Index: 5