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

Dataset: Open Web Text

Neuron 2962 in Layer 5

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: 4.8121. Min Range: -4.8121

Max Act: 4.8075. Min Act: -0.1700

Data Index: 8572653 (Open Web Text)

Max Activating Token Index: 818

Text #1

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.8121. Min Act: -0.1700

Data Index: 3271465 (Open Web Text)

Max Activating Token Index: 1013

Text #2

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.6828. Min Act: -0.1700

Data Index: 5550279 (Open Web Text)

Max Activating Token Index: 914

Text #3

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.6341. Min Act: -0.1700

Data Index: 5593925 (Open Web Text)

Max Activating Token Index: 498

Text #4

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.6797. Min Act: -0.1700

Data Index: 3271466 (Open Web Text)

Max Activating Token Index: 807

Text #5

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.6238. Min Act: -0.1700

Data Index: 6954861 (Open Web Text)

Max Activating Token Index: 527

Text #6

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.6098. Min Act: -0.1700

Data Index: 6226844 (Open Web Text)

Max Activating Token Index: 919

Text #7

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.6036. Min Act: -0.1700

Data Index: 2612835 (Open Web Text)

Max Activating Token Index: 403

Text #8

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.5724. Min Act: -0.1700

Data Index: 1734545 (Open Web Text)

Max Activating Token Index: 585

Text #9

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.6219. Min Act: -0.1700

Data Index: 3202308 (Open Web Text)

Max Activating Token Index: 883

Text #10

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.5761. Min Act: -0.1700

Data Index: 4862700 (Open Web Text)

Max Activating Token Index: 789

Text #11

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.5449. Min Act: -0.1700

Data Index: 783961 (Open Web Text)

Max Activating Token Index: 370

Text #12

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.5263. Min Act: -0.1700

Data Index: 6797060 (Open Web Text)

Max Activating Token Index: 941

Text #13

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.5377. Min Act: -0.1700

Data Index: 7888818 (Open Web Text)

Max Activating Token Index: 875

Text #14

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.5090. Min Act: -0.1700

Data Index: 5563761 (Open Web Text)

Max Activating Token Index: 957

Text #15

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.4579. Min Act: -0.1700

Data Index: 5727545 (Open Web Text)

Max Activating Token Index: 393

Text #16

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.5340. Min Act: -0.1700

Data Index: 5013734 (Open Web Text)

Max Activating Token Index: 550

Text #17

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.4526. Min Act: -0.1700

Data Index: 5549427 (Open Web Text)

Max Activating Token Index: 313

Text #18

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.4585. Min Act: -0.1700

Data Index: 7776531 (Open Web Text)

Max Activating Token Index: 458

Text #19

Max Range: 4.8121. Min Range: -4.8121

Max Act: 4.4322. Min Act: -0.1700

Data Index: 1482622 (Open Web Text)

Max Activating Token Index: 888