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

Dataset: Open Web Text

Neuron 1681 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: 1.5646. Min Range: -1.5646

Max Act: 1.5646. Min Act: -0.1700

Data Index: 381600 (Open Web Text)

Max Activating Token Index: 81

Text #1

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.5562. Min Act: -0.1700

Data Index: 7388315 (Open Web Text)

Max Activating Token Index: 581

Text #2

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.5599. Min Act: -0.1700

Data Index: 92470 (Open Web Text)

Max Activating Token Index: 365

Text #3

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.5145. Min Act: -0.1700

Data Index: 7409075 (Open Web Text)

Max Activating Token Index: 297

Text #4

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.4960. Min Act: -0.1700

Data Index: 4258427 (Open Web Text)

Max Activating Token Index: 677

Text #5

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.4981. Min Act: -0.1700

Data Index: 7614555 (Open Web Text)

Max Activating Token Index: 979

Text #6

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.4754. Min Act: -0.1700

Data Index: 6203968 (Open Web Text)

Max Activating Token Index: 615

Text #7

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.4766. Min Act: -0.1700

Data Index: 8826847 (Open Web Text)

Max Activating Token Index: 486

Text #8

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.4761. Min Act: -0.1700

Data Index: 8556523 (Open Web Text)

Max Activating Token Index: 595

Text #9

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.4652. Min Act: -0.1700

Data Index: 1108818 (Open Web Text)

Max Activating Token Index: 930

Text #10

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.4618. Min Act: -0.1700

Data Index: 2922901 (Open Web Text)

Max Activating Token Index: 34

Text #11

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.4630. Min Act: -0.1700

Data Index: 5263003 (Open Web Text)

Max Activating Token Index: 389

Text #12

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.4432. Min Act: -0.1700

Data Index: 5194192 (Open Web Text)

Max Activating Token Index: 55

Text #13

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.4581. Min Act: -0.1700

Data Index: 6999800 (Open Web Text)

Max Activating Token Index: 402

Text #14

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.4561. Min Act: -0.1700

Data Index: 7231805 (Open Web Text)

Max Activating Token Index: 962

Text #15

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.4353. Min Act: -0.1700

Data Index: 8431540 (Open Web Text)

Max Activating Token Index: 229

Text #16

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.4402. Min Act: -0.1700

Data Index: 6709044 (Open Web Text)

Max Activating Token Index: 987

Text #17

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.4513. Min Act: -0.1700

Data Index: 4807653 (Open Web Text)

Max Activating Token Index: 503

Text #18

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.4416. Min Act: -0.1700

Data Index: 385163 (Open Web Text)

Max Activating Token Index: 608

Text #19

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.4357. Min Act: -0.1700

Data Index: 2342707 (Open Web Text)

Max Activating Token Index: 541