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

Dataset: Open Web Text

Neuron 1452 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: 4.8678. Min Range: -4.8678

Max Act: 4.8647. Min Act: -0.1700

Data Index: 4805394 (Open Web Text)

Max Activating Token Index: 816

Text #1

Max Range: 4.8678. Min Range: -4.8678

Max Act: 4.8125. Min Act: -0.1700

Data Index: 1865528 (Open Web Text)

Max Activating Token Index: 531

Text #2

Max Range: 4.8678. Min Range: -4.8678

Max Act: 4.8469. Min Act: -0.1700

Data Index: 6991891 (Open Web Text)

Max Activating Token Index: 592

Text #3

Max Range: 4.8678. Min Range: -4.8678

Max Act: 4.8562. Min Act: -0.1700

Data Index: 6750223 (Open Web Text)

Max Activating Token Index: 531

Text #4

Max Range: 4.8678. Min Range: -4.8678

Max Act: 4.8591. Min Act: -0.1700

Data Index: 6286860 (Open Web Text)

Max Activating Token Index: 48

Text #5

Max Range: 4.8678. Min Range: -4.8678

Max Act: 4.8588. Min Act: -0.1700

Data Index: 6065965 (Open Web Text)

Max Activating Token Index: 412

Text #6

Max Range: 4.8678. Min Range: -4.8678

Max Act: 4.8678. Min Act: -0.1700

Data Index: 5840649 (Open Web Text)

Max Activating Token Index: 171

Text #7

Max Range: 4.8678. Min Range: -4.8678

Max Act: 4.8418. Min Act: -0.1700

Data Index: 5390375 (Open Web Text)

Max Activating Token Index: 451

Text #8

Max Range: 4.8678. Min Range: -4.8678

Max Act: 4.7723. Min Act: -0.1700

Data Index: 4478602 (Open Web Text)

Max Activating Token Index: 576

Text #9

Max Range: 4.8678. Min Range: -4.8678

Max Act: 4.7327. Min Act: -0.1700

Data Index: 5858074 (Open Web Text)

Max Activating Token Index: 634

Text #10

Max Range: 4.8678. Min Range: -4.8678

Max Act: 4.7649. Min Act: -0.1700

Data Index: 4529385 (Open Web Text)

Max Activating Token Index: 701

Text #11

Max Range: 4.8678. Min Range: -4.8678

Max Act: 4.7656. Min Act: -0.1700

Data Index: 6670407 (Open Web Text)

Max Activating Token Index: 446

Text #12

Max Range: 4.8678. Min Range: -4.8678

Max Act: 4.6910. Min Act: -0.1700

Data Index: 8294527 (Open Web Text)

Max Activating Token Index: 997

Text #13

Max Range: 4.8678. Min Range: -4.8678

Max Act: 4.6980. Min Act: -0.1700

Data Index: 139530 (Open Web Text)

Max Activating Token Index: 542

Text #14

Max Range: 4.8678. Min Range: -4.8678

Max Act: 4.7012. Min Act: -0.1700

Data Index: 6324184 (Open Web Text)

Max Activating Token Index: 555

Text #15

Max Range: 4.8678. Min Range: -4.8678

Max Act: 4.7249. Min Act: -0.1700

Data Index: 1125238 (Open Web Text)

Max Activating Token Index: 816

Text #16

Max Range: 4.8678. Min Range: -4.8678

Max Act: 4.6925. Min Act: -0.1700

Data Index: 2992142 (Open Web Text)

Max Activating Token Index: 207

Text #17

Max Range: 4.8678. Min Range: -4.8678

Max Act: 4.6334. Min Act: -0.1700

Data Index: 1545723 (Open Web Text)

Max Activating Token Index: 479

Text #18

Max Range: 4.8678. Min Range: -4.8678

Max Act: 4.6504. Min Act: -0.1700

Data Index: 6969973 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.8678. Min Range: -4.8678

Max Act: 4.6446. Min Act: -0.1700

Data Index: 3157087 (Open Web Text)

Max Activating Token Index: 840