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

Dataset: Open Web Text

Neuron 285 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: 4.1997. Min Range: -4.1997

Max Act: 4.1997. Min Act: -0.1700

Data Index: 3077130 (Open Web Text)

Max Activating Token Index: 658

Text #1

Max Range: 4.1997. Min Range: -4.1997

Max Act: 4.1889. Min Act: -0.1700

Data Index: 233878 (Open Web Text)

Max Activating Token Index: 686

Text #2

Max Range: 4.1997. Min Range: -4.1997

Max Act: 4.1664. Min Act: -0.1700

Data Index: 3487595 (Open Web Text)

Max Activating Token Index: 740

Text #3

Max Range: 4.1997. Min Range: -4.1997

Max Act: 4.1713. Min Act: -0.1700

Data Index: 6724503 (Open Web Text)

Max Activating Token Index: 596

Text #4

Max Range: 4.1997. Min Range: -4.1997

Max Act: 4.1228. Min Act: -0.1700

Data Index: 8243186 (Open Web Text)

Max Activating Token Index: 61

Text #5

Max Range: 4.1997. Min Range: -4.1997

Max Act: 4.1331. Min Act: -0.1700

Data Index: 3394428 (Open Web Text)

Max Activating Token Index: 640

Text #6

Max Range: 4.1997. Min Range: -4.1997

Max Act: 4.1019. Min Act: -0.1700

Data Index: 8223453 (Open Web Text)

Max Activating Token Index: 144

Text #7

Max Range: 4.1997. Min Range: -4.1997

Max Act: 4.0800. Min Act: -0.1700

Data Index: 8085579 (Open Web Text)

Max Activating Token Index: 732

Text #8

Max Range: 4.1997. Min Range: -4.1997

Max Act: 4.0970. Min Act: -0.1700

Data Index: 4373109 (Open Web Text)

Max Activating Token Index: 792

Text #9

Max Range: 4.1997. Min Range: -4.1997

Max Act: 4.0852. Min Act: -0.1700

Data Index: 6921737 (Open Web Text)

Max Activating Token Index: 157

Text #10

Max Range: 4.1997. Min Range: -4.1997

Max Act: 4.0801. Min Act: -0.1700

Data Index: 3672211 (Open Web Text)

Max Activating Token Index: 630

Text #11

Max Range: 4.1997. Min Range: -4.1997

Max Act: 4.0795. Min Act: -0.1700

Data Index: 3337648 (Open Web Text)

Max Activating Token Index: 438

Text #12

Max Range: 4.1997. Min Range: -4.1997

Max Act: 4.0832. Min Act: -0.1700

Data Index: 6621818 (Open Web Text)

Max Activating Token Index: 416

Text #13

Max Range: 4.1997. Min Range: -4.1997

Max Act: 4.0972. Min Act: -0.1700

Data Index: 6318634 (Open Web Text)

Max Activating Token Index: 488

Text #14

Max Range: 4.1997. Min Range: -4.1997

Max Act: 4.0365. Min Act: -0.1700

Data Index: 2840419 (Open Web Text)

Max Activating Token Index: 125

Text #15

Max Range: 4.1997. Min Range: -4.1997

Max Act: 4.0677. Min Act: -0.1700

Data Index: 893382 (Open Web Text)

Max Activating Token Index: 564

Text #16

Max Range: 4.1997. Min Range: -4.1997

Max Act: 4.0615. Min Act: -0.1700

Data Index: 2510321 (Open Web Text)

Max Activating Token Index: 104

Text #17

Max Range: 4.1997. Min Range: -4.1997

Max Act: 4.0644. Min Act: -0.1700

Data Index: 1351884 (Open Web Text)

Max Activating Token Index: 944

Text #18

Max Range: 4.1997. Min Range: -4.1997

Max Act: 4.0486. Min Act: -0.1700

Data Index: 7188072 (Open Web Text)

Max Activating Token Index: 391

Text #19

Max Range: 4.1997. Min Range: -4.1997

Max Act: 4.0484. Min Act: -0.1700

Data Index: 2342616 (Open Web Text)

Max Activating Token Index: 100