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

Dataset: Open Web Text

Neuron 397 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: 4.6080. Min Range: -4.6080

Max Act: 4.6080. Min Act: -0.1700

Data Index: 264162 (Open Web Text)

Max Activating Token Index: 423

Text #1

Max Range: 4.6080. Min Range: -4.6080

Max Act: 4.5630. Min Act: -0.1700

Data Index: 5741371 (Open Web Text)

Max Activating Token Index: 344

Text #2

Max Range: 4.6080. Min Range: -4.6080

Max Act: 4.4948. Min Act: -0.1700

Data Index: 4734121 (Open Web Text)

Max Activating Token Index: 738

Text #3

Max Range: 4.6080. Min Range: -4.6080

Max Act: 4.3153. Min Act: -0.1700

Data Index: 7179642 (Open Web Text)

Max Activating Token Index: 257

Text #4

Max Range: 4.6080. Min Range: -4.6080

Max Act: 4.3235. Min Act: -0.1700

Data Index: 2143278 (Open Web Text)

Max Activating Token Index: 591

Text #5

Max Range: 4.6080. Min Range: -4.6080

Max Act: 4.3134. Min Act: -0.1700

Data Index: 5768288 (Open Web Text)

Max Activating Token Index: 651

Text #6

Max Range: 4.6080. Min Range: -4.6080

Max Act: 4.2692. Min Act: -0.1700

Data Index: 1569981 (Open Web Text)

Max Activating Token Index: 624

Text #7

Max Range: 4.6080. Min Range: -4.6080

Max Act: 4.2741. Min Act: -0.1700

Data Index: 7951614 (Open Web Text)

Max Activating Token Index: 139

Text #8

Max Range: 4.6080. Min Range: -4.6080

Max Act: 4.2670. Min Act: -0.1700

Data Index: 7313993 (Open Web Text)

Max Activating Token Index: 545

Text #9

Max Range: 4.6080. Min Range: -4.6080

Max Act: 4.2533. Min Act: -0.1700

Data Index: 3943122 (Open Web Text)

Max Activating Token Index: 328

Text #10

Max Range: 4.6080. Min Range: -4.6080

Max Act: 4.3275. Min Act: -0.1700

Data Index: 1254342 (Open Web Text)

Max Activating Token Index: 522

Text #11

Max Range: 4.6080. Min Range: -4.6080

Max Act: 4.2427. Min Act: -0.1700

Data Index: 1152871 (Open Web Text)

Max Activating Token Index: 511

Text #12

Max Range: 4.6080. Min Range: -4.6080

Max Act: 4.2733. Min Act: -0.1700

Data Index: 648976 (Open Web Text)

Max Activating Token Index: 597

Text #13

Max Range: 4.6080. Min Range: -4.6080

Max Act: 4.2562. Min Act: -0.1700

Data Index: 3471211 (Open Web Text)

Max Activating Token Index: 652

Text #14

Max Range: 4.6080. Min Range: -4.6080

Max Act: 4.2274. Min Act: -0.1700

Data Index: 4106048 (Open Web Text)

Max Activating Token Index: 504

Text #15

Max Range: 4.6080. Min Range: -4.6080

Max Act: 4.2063. Min Act: -0.1700

Data Index: 8173881 (Open Web Text)

Max Activating Token Index: 564

Text #16

Max Range: 4.6080. Min Range: -4.6080

Max Act: 4.2036. Min Act: -0.1700

Data Index: 2491781 (Open Web Text)

Max Activating Token Index: 698

Text #17

Max Range: 4.6080. Min Range: -4.6080

Max Act: 4.1810. Min Act: -0.1700

Data Index: 1179390 (Open Web Text)

Max Activating Token Index: 13

Text #18

Max Range: 4.6080. Min Range: -4.6080

Max Act: 4.1928. Min Act: -0.1700

Data Index: 5721099 (Open Web Text)

Max Activating Token Index: 145

Text #19

Max Range: 4.6080. Min Range: -4.6080

Max Act: 4.2183. Min Act: -0.1700

Data Index: 2747125 (Open Web Text)

Max Activating Token Index: 28