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

Dataset: Open Web Text

Neuron 1375 in Layer 6

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: 4.0531. Min Range: -4.0531

Max Act: 4.0531. Min Act: -0.1700

Data Index: 7897192 (Open Web Text)

Max Activating Token Index: 462

Text #1

Max Range: 4.0531. Min Range: -4.0531

Max Act: 3.8108. Min Act: -0.1700

Data Index: 8316252 (Open Web Text)

Max Activating Token Index: 751

Text #2

Max Range: 4.0531. Min Range: -4.0531

Max Act: 3.7563. Min Act: -0.1700

Data Index: 2309161 (Open Web Text)

Max Activating Token Index: 487

Text #3

Max Range: 4.0531. Min Range: -4.0531

Max Act: 3.7705. Min Act: -0.1700

Data Index: 217109 (Open Web Text)

Max Activating Token Index: 574

Text #4

Max Range: 4.0531. Min Range: -4.0531

Max Act: 3.7442. Min Act: -0.1700

Data Index: 7501819 (Open Web Text)

Max Activating Token Index: 516

Text #5

Max Range: 4.0531. Min Range: -4.0531

Max Act: 3.7365. Min Act: -0.1700

Data Index: 8777633 (Open Web Text)

Max Activating Token Index: 327

Text #6

Max Range: 4.0531. Min Range: -4.0531

Max Act: 3.7023. Min Act: -0.1700

Data Index: 4561343 (Open Web Text)

Max Activating Token Index: 764

Text #7

Max Range: 4.0531. Min Range: -4.0531

Max Act: 3.7219. Min Act: -0.1700

Data Index: 2997828 (Open Web Text)

Max Activating Token Index: 953

Text #8

Max Range: 4.0531. Min Range: -4.0531

Max Act: 3.6767. Min Act: -0.1700

Data Index: 7015173 (Open Web Text)

Max Activating Token Index: 699

Text #9

Max Range: 4.0531. Min Range: -4.0531

Max Act: 3.7012. Min Act: -0.1700

Data Index: 2126536 (Open Web Text)

Max Activating Token Index: 479

Text #10

Max Range: 4.0531. Min Range: -4.0531

Max Act: 3.6925. Min Act: -0.1700

Data Index: 3375147 (Open Web Text)

Max Activating Token Index: 792

Text #11

Max Range: 4.0531. Min Range: -4.0531

Max Act: 3.6817. Min Act: -0.1700

Data Index: 5794078 (Open Web Text)

Max Activating Token Index: 132

Text #12

Max Range: 4.0531. Min Range: -4.0531

Max Act: 3.6620. Min Act: -0.1700

Data Index: 2661888 (Open Web Text)

Max Activating Token Index: 539

Text #13

Max Range: 4.0531. Min Range: -4.0531

Max Act: 3.6617. Min Act: -0.1700

Data Index: 4558270 (Open Web Text)

Max Activating Token Index: 390

Text #14

Max Range: 4.0531. Min Range: -4.0531

Max Act: 3.6579. Min Act: -0.1700

Data Index: 2422962 (Open Web Text)

Max Activating Token Index: 777

Text #15

Max Range: 4.0531. Min Range: -4.0531

Max Act: 3.6510. Min Act: -0.1700

Data Index: 4855231 (Open Web Text)

Max Activating Token Index: 994

Text #16

Max Range: 4.0531. Min Range: -4.0531

Max Act: 3.6379. Min Act: -0.1700

Data Index: 2699985 (Open Web Text)

Max Activating Token Index: 539

Text #17

Max Range: 4.0531. Min Range: -4.0531

Max Act: 3.6719. Min Act: -0.1700

Data Index: 40437 (Open Web Text)

Max Activating Token Index: 135

Text #18

Max Range: 4.0531. Min Range: -4.0531

Max Act: 3.6732. Min Act: -0.1700

Data Index: 348281 (Open Web Text)

Max Activating Token Index: 992

Text #19

Max Range: 4.0531. Min Range: -4.0531

Max Act: 3.6446. Min Act: -0.1700

Data Index: 5798878 (Open Web Text)

Max Activating Token Index: 968